© 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. 86556
    Prev
    Next
    INDEX
    Explanations

    condition, then, younger

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

    monarch / différent

    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
    রত্ব
    0.49
     دیجیت
    0.48
     Stad
    0.46
    谗
    0.46
     వీడియో
    0.45
     دهند
    0.45
     உற
    0.44
     Ethnicity
    0.44
     Nested
    0.43
     界
    0.43
    POSITIVE LOGITS
    .
    0.50
    し
    0.49
    caption
    0.46
    okit
    0.45
    ↵
    0.45
     Maroc
    0.45
    aidh
    0.44
    ỉ
    0.44
    uning
    0.44
     religiously
    0.44
    Activations Density 0.002%

    No Known Activations