© 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. 182131
    Prev
    Next
    INDEX
    Explanations

    thesis and cases

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

    analysis and detection

    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
    трон
    0.50
    шина
    0.48
     antih
    0.47
    дни
    0.47
    ЕС
    0.46
     много
    0.46
    анта
    0.46
    밤
    0.45
    стема
    0.44
    ين
    0.44
    POSITIVE LOGITS
     depende
    0.55
     aufgrund
    0.51
    aghe
    0.50
    ade
    0.48
    rq
    0.47
     单位
    0.46
     Auditors
    0.46
    too
    0.46
     குறிப்பிட
    0.46
    mast
    0.46
    Activations Density 0.000%

    No Known Activations