© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63694
    Prev
    Next
    INDEX
    Explanations

    unambiguous identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dismiss
    -0.84
    gements
    -0.77
    ladimir
    -0.74
     صوت
    -0.73
    šin
    -0.73
    spieler
    -0.73
     עלי
    -0.72
     varsity
    -0.72
     Dismiss
    -0.72
    ۥ
    -0.72
    POSITIVE LOGITS
     ambiguity
    4.78
     ambiguous
    4.63
     ambiguities
    3.78
    ambiguous
    3.73
    Amb
    3.23
     Amb
    3.22
     ambig
    3.02
    ambigu
    2.94
     ambigu
    2.91
    ambig
    2.81
    Activations Density 0.083%

    No Known Activations