© 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. 190343
    Prev
    Next
    INDEX
    Explanations

    non-standard words

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

    sounds most interesting

    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
     strict
    0.53
    写真
    0.45
    特
    0.45
    }^{
    0.44
    ルの
    0.44
     presumption
    0.43
    予想
    0.43
    特徴
    0.43
     stricter
    0.42
    強
    0.42
    POSITIVE LOGITS
    edor
    0.53
     Wedgwood
    0.50
     الي
    0.49
     hu
    0.46
     arbitr
    0.46
    ed
    0.45
     мая
    0.45
     обратно
    0.44
     그것
    0.44
     juntos
    0.43
    Activations Density 0.001%

    No Known Activations