© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 216604
    Prev
    Next
    INDEX
    Explanations

    regular, necessary, often, washing

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

    listing words and their following characters or words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     .)
    0.50
     فونٹ
    0.49
    .`);
    0.46
    bones
    0.46
    atthena
    0.45
     丶
    0.43
    硞
    0.42
     اله
    0.41
     topical
    0.41
    ointments
    0.41
    POSITIVE LOGITS
    ING
    0.48
     Melhor
    0.47
    meldung
    0.45
    как
    0.44
     według
    0.44
    Je
    0.44
    രി
    0.43
    wać
    0.43
    -
    0.43
    ране
    0.43
    Activations Density 0.000%

    No Known Activations