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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 162090
    Prev
    Next
    INDEX
    Explanations

    mentions of future state

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

    drug, Master, read, fundamental, favourite, belong, siblings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    λη
    0.46
     Bên
    0.46
    の見
    0.45
    内
    0.44
     للف
    0.43
     McLaughlin
    0.43
     Trung
    0.43
     পররাষ্ট্র
    0.43
     экране
    0.43
    కరణ
    0.42
    POSITIVE LOGITS
     GUAR
    0.47
    Didn
    0.45
    GUAR
    0.44
    PARATOR
    0.43
    ▻
    0.43
    wrapperEl
    0.42
     AMOUNT
    0.42
    righteous
    0.42
    प्रेम
    0.42
    daftar
    0.42
    Activations Density 0.000%

    No Known Activations