© 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. 234572
    Prev
    Next
    INDEX
    Explanations

    streak-free shine

    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
     tangent
    0.52
    癀
    0.47
     predecess
    0.43
     uninter
    0.43
     foes
    0.43
    েনের
    0.42
     tướng
    0.42
     incoherent
    0.42
    า
    0.42
     berbentuk
    0.42
    POSITIVE LOGITS
    ã
    0.51
    volunteer
    0.49
    sq
    0.48
    lar
    0.47
    ng
    0.46
    Carolina
    0.45
    SCPC
    0.45
    ง
    0.44
    kappa
    0.44
    ICPSR
    0.44
    Activations Density 0.000%

    No Known Activations