© 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. 27460
    Prev
    Next
    INDEX
    Explanations

    leading innovation and developing CRM

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

    questions about capabilities and costs

    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
    sel
    0.48
    sy
    0.45
    ims
    0.44
    se
    0.42
    ᅲ
    0.42
     डेविड
    0.41
    superior
    0.41
    sm
    0.41
    "
    0.41
    ancy
    0.40
    POSITIVE LOGITS
    رداری
    0.60
     alimentos
    0.57
    راہ
    0.57
    ریر
    0.55
     atteindre
    0.54
    MEDICAL
    0.52
    ourent
    0.50
    Agregar
    0.50
     bebidas
    0.49
     অদ
    0.49
    Activations Density 0.000%

    No Known Activations