© 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. 65533
    Prev
    Next
    INDEX
    Explanations

    prickly spines thorns hedgehog cactus

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

    words and terms related to spiky or thorny objects (like hedgehogs, prickly pears, spikes, thorns).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Ponds
    -0.87
    大橋
    -0.84
     fumar
    -0.81
    putra
    -0.81
     актри
    -0.79
    araman
    -0.74
     trypto
    -0.74
     goldfish
    -0.73
    を追
    -0.73
     подру
    -0.72
    POSITIVE LOGITS
     thorns
    2.19
     spines
    2.13
     prickly
    1.95
     prick
    1.84
     spikes
    1.84
     thorn
    1.80
    刺
    1.63
     thorny
    1.61
     hedgehog
    1.59
     barbed
    1.52
    Activations Density 0.030%

    No Known Activations