© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152688
    Prev
    Next
    INDEX
    Explanations

    variable, clipboard, errors, basket, messages

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

    checks and states

    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
     ე
    0.46
    Checkbox
    0.39
    טור
    0.38
    之地
    0.38
     द
    0.37
     तिर
    0.36
     ఆడ
    0.35
    minify
    0.35
     मिल्
    0.35
    㶲
    0.35
    POSITIVE LOGITS
     accumulated
    0.59
     currently
    0.56
     reciente
    0.54
     résult
    0.52
     recente
    0.51
     recent
    0.50
     ప్రస్తుతం
    0.49
     attualmente
    0.49
    Currently
    0.48
     acumul
    0.48
    Activations Density 0.013%

    No Known Activations