© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119287
    Prev
    Next
    INDEX
    Explanations

    animal displays and behaviors

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptions of animal mating behaviors and reproductive strategies.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects mentions of copulation or mating (references to sexual reproductive contact).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ּוֹ
    -0.94
    λικ
    -0.90
    懵
    -0.86
     afirmou
    -0.85
    וֹ
    -0.83
    ichteten
    -0.83
    っぱい
    -0.82
     presiden
    -0.82
    seamnă
    -0.82
     quai
    -0.81
    POSITIVE LOGITS
     defensive
    1.20
     folded
    0.99
     defense
    0.99
     Inflation
    0.98
     displays
    0.97
    Defensive
    0.96
     alarm
    0.91
     defensively
    0.90
     specialized
    0.90
     warning
    0.88
    Activations Density 0.084%

    No Known Activations