© 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. 84846
    Prev
    Next
    INDEX
    Explanations

    basic overview

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

    costing, staging, information, cancer, cosmology

    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
     Duma
    0.46
     Upton
    0.44
     Osw
    0.44
    вір
    0.43
    കര്‍
    0.42
    榎
    0.41
    getUserMedia
    0.41
    UniqueIdentifier
    0.41
     duy
    0.41
    َع
    0.41
    POSITIVE LOGITS
    nen
    0.56
    hur
    0.55
    hmen
    0.52
     定义
    0.50
     धोखा
    0.49
    rer
    0.49
    err
    0.49
    jne
    0.49
    patri
    0.48
    lük
    0.48
    Activations Density 0.001%

    No Known Activations