© 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. 146224
    Prev
    Next
    INDEX
    Explanations

    sale of stock

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

    religious or cultural context

    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
     ១
    0.51
     bazar
    0.46
     celebrado
    0.46
     resize
    0.43
     yun
    0.43
    𝑮
    0.43
     glaze
    0.43
     aby
    0.42
     goto
    0.42
     为了
    0.42
    POSITIVE LOGITS
    AIC
    0.51
    ारे
    0.49
    ސް
    0.48
    ファー
    0.47
    멕
    0.46
    ו
    0.46
     LTC
    0.45
    Conserv
    0.44
    کی
    0.44
    راک
    0.44
    Activations Density 0.000%

    No Known Activations