© 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. 62206
    Prev
    Next
    INDEX
    Explanations

    holding harmless from

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

    leverage and comparison

    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
    ை
    0.48
    嵐
    0.47
     ਹ
    0.46
     quizá
    0.46
    𝗱
    0.46
    蓄
    0.45
    Gregor
    0.44
    ⚤
    0.44
    ❆
    0.44
    doubt
    0.44
    POSITIVE LOGITS
     leveraged
    0.55
     leverage
    0.53
    0.53
     leverages
    0.52
    '
    0.50
     Leverage
    0.49
     rollback
    0.47
     engagements
    0.46
     deployments
    0.46
     Salesforce
    0.45
    Activations Density 0.000%

    No Known Activations