© 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. 22-GEMMASCOPE-RES-131K
    7. 15039
    Prev
    Next
    INDEX
    Explanations

    words starting with am

    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_22/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
     alcuni
    -2.81
    。
    -2.58
     alcune
    -2.58
     molte
    -2.53
    });
    -2.50
     asociaciones
    -2.50
     utilizzo
    -2.45
     evaluaciones
    -2.45
    ];
    -2.41
     utilizzata
    -2.34
    POSITIVE LOGITS
    ↵↵
    3.25
    .
    2.58
     There
    2.58
    ↵
    2.42
    挲
    2.22
     这
    2.19
     这个
    2.16
    綃
    2.11
    h
    2.09
     This
    2.08
    Activations Density 0.030%

    No Known Activations