© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7772
    Prev
    Next
    INDEX
    Explanations

    type IV classification

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

    This neuron strongly fires on second‐person possessive pronouns (e.g. “your” or its equivalents in other languages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cssMode
    0.80
     музея
    0.79
    ónio
    0.76
    煕
    0.75
     апреле
    0.75
    ྛ
    0.74
    comics
    0.74
    ómo
    0.73
    Echo
    0.71
    cornell
    0.71
    POSITIVE LOGITS
     a
    0.90
     can
    0.88
     subjective
    0.87
     all
    0.86
     compulsive
    0.86
     prophylactic
    0.84
     concerted
    0.83
     synergistic
    0.83
     accelerated
    0.83
     huk
    0.82
    Activations Density 0.003%

    No Known Activations