© 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. 26212
    Prev
    Next
    INDEX
    Explanations

    code and markup elements

    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
    hasilkan
    -0.86
    Én
    -0.85
    Transcriptie
    -0.85
     estudia
    -0.83
    feeding
    -0.82
     zina
    -0.82
    ופן
    -0.82
     HUNTER
    -0.82
     LAWRENCE
    -0.81
     grosse
    -0.80
    POSITIVE LOGITS
    omin
    0.94
    </tbody>
    0.90
    <h4>
    0.87
    For
    0.85
    plasia
    0.83
    <h5>
    0.82
    PC
    0.81
     ha
    0.81
     [-
    0.80
    olia
    0.79
    Activations Density 0.048%

    No Known Activations