© 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. 79643
    Prev
    Next
    INDEX
    Explanations

    rattlesnake, inconsistencies

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

    people, she, now, Sometimes

    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
    kron
    0.46
     stabil
    0.46
     u
    0.45
     stacked
    0.45
     인한
    0.45
     prediksi
    0.45
     >
    0.44
     challenges
    0.44
     sustainability
    0.44
     消
    0.44
    POSITIVE LOGITS
    чева
    0.46
    Are
    0.44
    льник
    0.44
    Warrior
    0.44
    Acrylic
    0.44
    ႆ
    0.44
    Cancel
    0.44
    Want
    0.44
    Fill
    0.44
    Plays
    0.43
    Activations Density 0.002%

    No Known Activations