© 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. 249225
    Prev
    Next
    INDEX
    Explanations

    content on social media or news

    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
    ステム
    0.50
    計測
    0.49
     constriction
    0.46
     IRB
    0.44
    tal
    0.43
    IAC
    0.42
    increment
    0.41
    逓
    0.41
    inetics
    0.41
     NAG
    0.41
    POSITIVE LOGITS
    Doesn
    0.51
    manager
    0.46
    sentiment
    0.44
    MyShop
    0.43
     và
    0.43
     direção
    0.42
    From
    0.42
     رئيس
    0.42
     veux
    0.42
    려고
    0.41
    Activations Density 0.000%

    No Known Activations