© 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. 232973
    Prev
    Next
    INDEX
    Explanations

    reinforcement placement work interest

    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
    ran
    0.48
    x
    0.45
    yn
    0.45
    後
    0.45
    wald
    0.44
    svc
    0.44
     مِن
    0.43
     confl
    0.43
    squa
    0.43
    cmap
    0.42
    POSITIVE LOGITS
     additions
    0.47
    בר
    0.46
    マー
    0.46
    ग्रियों
    0.46
     attendre
    0.46
    茄
    0.46
    特別な
    0.45
     फ्ल
    0.45
     interess
    0.45
    工作的
    0.44
    Activations Density 0.003%

    No Known Activations