© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129942
    Prev
    Next
    INDEX
    Explanations

    code components and punctuation

    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_10/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
     Einzelnen
    -1.10
     deleterious
    -1.09
     besonderen
    -1.08
     traditionellen
    -1.08
     as
    -1.04
     compuestos
    -1.03
    经过
    -1.02
     eachother
    -1.00
    mrow
    -1.00
     plásticos
    -0.99
    POSITIVE LOGITS
     '/':
    1.45
    lysm
    1.38
    nev
    1.35
    mOn
    1.35
    zzet
    1.30
    </h1>
    1.29
    unno
    1.27
    chsel
    1.27
    )');
    1.24
     {}));
    1.23
    Activations Density 0.088%

    No Known Activations