© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26996
    Prev
    Next
    INDEX
    Explanations

    codes and citations

    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
    );
    -1.12
    ]
    -1.10
     it
    -1.06
    も多く
    -1.03
     エリア
    -1.02
    你有
    -0.94
    )
    -0.94
     its
    -0.92
     periods
    -0.92
     vedno
    -0.91
    POSITIVE LOGITS
    𓆩
    1.15
    spunkt
    1.14
    Срок
    1.13
    */}
    1.12
    "}}
    1.08
    </i>
    1.06
     mariposa
    1.05
     كيفية
    1.04
    ycle
    1.02
     jade
    1.02
    Activations Density 0.023%

    No Known Activations