© 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. 229218
    Prev
    Next
    INDEX
    Explanations

    organization and management

    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
    žad
    0.53
     otvor
    0.52
     čemu
    0.50
    getFullName
    0.49
    牦
    0.47
    ől
    0.47
    utan
    0.46
     بنایا
    0.46
    鹂
    0.46
     अधिनियम
    0.46
    POSITIVE LOGITS
     products
    0.53
     another
    0.52
    (
    0.50
    *
    0.50
     adaptations
    0.49
     sores
    0.48
     samples
    0.47
     instability
    0.47
    פ
    0.47
    AT
    0.47
    Activations Density 0.000%

    No Known Activations