© 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. 73754
    Prev
    Next
    INDEX
    Explanations

    represents financial information or articles

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

    unless you

    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
     nêu
    0.49
     собстве
    0.45
    тың
    0.45
     là
    0.45
    ,*/}
    0.44
    ભાઈ
    0.44
     salga
    0.44
     моём
    0.43
     nhìn
    0.43
     cael
    0.43
    POSITIVE LOGITS
    。
    0.46
    ORTH
    0.46
    َان
    0.45
    andidates
    0.45
    onders
    0.43
    曖
    0.43
    ។
    0.42
     candidates
    0.41
    ians
    0.41
    λη
    0.41
    Activations Density 0.001%

    No Known Activations