© 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. 148399
    Prev
    Next
    INDEX
    Explanations

    saving money

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

    crime and investigation

    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
    鱒
    0.58
    カテゴ
    0.54
    숫
    0.51
    模板
    0.50
     énon
    0.50
    阆
    0.50
    鳟
    0.50
    énd
    0.50
    สื่อ
    0.50
    内部
    0.50
    POSITIVE LOGITS
    ↵
    0.50
     detective
    0.46
     $,
    0.46
    0
    0.45
    uns
    0.45
    2
    0.44
     cumbersome
    0.44
    sess
    0.43
    DCs
    0.42
     su
    0.42
    Activations Density 0.000%

    No Known Activations