© 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. 219236
    Prev
    Next
    INDEX
    Explanations

    making edits, experience required

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

    context, consequences, reasons, actions

    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
     অনিবার
    0.48
     ","
    0.48
    EM
    0.46
     galore
    0.45
     电
    0.45
     листопада
    0.44
     Seminary
    0.44
     发布
    0.44
     ','
    0.42
     Broccoli
    0.42
    POSITIVE LOGITS
    م
    0.59
     belirli
    0.46
    垀
    0.44
    belly
    0.44
    勁
    0.44
    ف
    0.44
    ن
    0.44
     giai
    0.43
    匍
    0.43
    lager
    0.43
    Activations Density 0.001%

    No Known Activations