© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83665
    Prev
    Next
    INDEX
    Explanations

    foo bar, Eb Bb, p dT, true false, meningioma tissue

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

    patterns of tabular or grid-like data.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    bakar
    -1.02
    jectile
    -0.94
    tyg
    -0.94
     ФИ
    -0.90
    jango
    -0.90
     pieni
    -0.90
     zvuky
    -0.89
     соответству
    -0.89
    raison
    -0.88
     Για
    -0.88
    POSITIVE LOGITS
     etc
    0.92
     Sometimes
    0.86
    ...");
    0.85
    neling
    0.84
     may
    0.84
    enes
    0.84
    ắn
    0.84
    敍
    0.82
     with
    0.82
     teilweise
    0.82
    Activations Density 0.003%

    No Known Activations