© 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. 168569
    Prev
    Next
    INDEX
    Explanations

    listing, monthly, invasive, general, portal

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

    acknowledges, me, force, localStorage, without

    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
    etzt
    0.53
    lcii
    0.52
    ৯
    0.51
     Seconds
    0.51
    bv
    0.51
    мережа
    0.51
     πρώ
    0.48
    優先
    0.48
    %>%
    0.48
    গিরই
    0.48
    POSITIVE LOGITS
    на
    0.46
    unis
    0.45
    ви
    0.44
     QUEST
    0.42
    复制代码
    0.42
    с
    0.41
    otha
    0.41
    о
    0.40
    adins
    0.40
    quest
    0.40
    Activations Density 0.000%

    No Known Activations