© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136381
    Prev
    Next
    INDEX
    Explanations

    Class, improving, city-level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    িস
    0.47
    ad
    0.43
    Causes
    0.43
    Model
    0.43
    is
    0.42
    ল
    0.42
    લ્સ
    0.42
    رح
    0.42
    造成
    0.42
    ak
    0.41
    POSITIVE LOGITS
     banknotes
    0.46
    başı
    0.46
    𝘖
    0.46
     bitten
    0.46
    𝘯
    0.46
     pale
    0.45
    িয়নের
    0.44
     bluish
    0.44
     untrue
    0.44
     dzien
    0.43
    Activations Density 0.000%

    No Known Activations