© 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. 45457
    Prev
    Next
    INDEX
    Explanations

    permanent states or objects

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

    The neuron specifically detects occurrences of the word “permanent.”

    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
    satunya
    -0.93
     mergul
    -0.87
    蟥
    -0.81
    meden
    -0.79
     initi
    -0.79
     abbond
    -0.79
     pondered
    -0.78
    jenige
    -0.78
     antigo
    -0.77
     tumble
    -0.77
    POSITIVE LOGITS
    permanent
    1.35
     Permanent
    1.32
     permanent
    1.27
    Permanent
    1.26
     fixture
    1.19
     fixtures
    1.13
     residence
    1.09
     residency
    1.02
    Perman
    1.00
     resident
    0.98
    Activations Density 0.027%

    No Known Activations