© 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. 237284
    Prev
    Next
    INDEX
    Explanations

    crushing

    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
    ه
    0.57
     kupu
    0.52
    ⺆
    0.52
    =((
    0.50
    冋
    0.50
     $((
    0.48
    taa
    0.48
    仳
    0.48
    lysis
    0.46
    kapal
    0.46
    POSITIVE LOGITS
    description
    0.48
    announce
    0.46
    Description
    0.42
     quảng
    0.42
     announce
    0.42
     anyway
    0.41
     Complex
    0.41
    Advertise
    0.41
    ی
    0.41
    ق
    0.40
    Activations Density 0.001%

    No Known Activations