© 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. 250891
    Prev
    Next
    INDEX
    Explanations

    price reductions

    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
    途径
    0.50
     намного
    0.49
     гораздо
    0.48
     装
    0.46
     জো
    0.45
     失
    0.45
     继续
    0.44
     夜
    0.44
     ቅር
    0.44
     préférable
    0.44
    POSITIVE LOGITS
     tease
    0.50
    مک
    0.49
    گم
    0.47
    گن
    0.47
     cognition
    0.46
    گ
    0.44
    бка
    0.44
     agony
    0.43
    quam
    0.42
    ۲۰
    0.42
    Activations Density 0.000%

    No Known Activations