© 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. 221595
    Prev
    Next
    INDEX
    Explanations

    posted in, Court in, Racing mode, quarterly basis

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

    actions followed by outcomes

    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
     چک
    0.50
    訒
    0.48
    CheckBox
    0.45
    用水
    0.45
    に使用
    0.45
     BuildableName
    0.42
    訛
    0.42
    クリ
    0.42
    名字
    0.42
     immobili
    0.42
    POSITIVE LOGITS
     Sheldon
    0.45
     Metropolis
    0.44
    QueryResult
    0.44
     maanden
    0.44
     Governments
    0.43
     Winners
    0.43
    ="
    0.43
    =”
    0.43
    Subs
    0.43
     Lack
    0.42
    Activations Density 0.000%

    No Known Activations