© 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. 165903
    Prev
    Next
    INDEX
    Explanations

    example phrases

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

    evaluation and decision

    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
     बचाया
    0.48
     sayam
    0.46
    –
    0.45
    구요
    0.45
    dashed
    0.45
    invas
    0.44
     repudiandae
    0.44
    dana
    0.43
    nano
    0.43
    )’
    0.43
    POSITIVE LOGITS
    殼
    0.48
    ﻑ
    0.47
     finca
    0.45
     বাড়ির
    0.45
    TISE
    0.44
     topLeft
    0.44
    紳
    0.43
    ావ
    0.43
    ﾞ
    0.43
    フィー
    0.42
    Activations Density 0.000%

    No Known Activations