© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12661
    Prev
    Next
    INDEX
    Explanations

    a pilgrimage or off

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

    **establishing credibility and purpose**

    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
    囪
    0.43
     znamená
    0.42
    FLO
    0.42
     இப்போது
    0.42
    ፈጥ
    0.42
    赋予
    0.42
    胝
    0.41
    繼續
    0.41
    啖
    0.41
    嗕
    0.41
    POSITIVE LOGITS
     Mi
    0.46
     WAT
    0.46
     supernat
    0.46
     स्थलों
    0.44
     علامه
    0.44
     plais
    0.43
     করিয়৷
    0.43
     עד
    0.43
     ".
    0.42
     писатель
    0.42
    Activations Density 0.000%

    No Known Activations