© 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. 197879
    Prev
    Next
    INDEX
    Explanations

    legal or descriptive phrases

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

    directory and filename selection

    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
    वारीत
    0.50
    <unused86>
    0.50
     Dusk
    0.49
     Laugh
    0.49
     Beans
    0.49
     januar
    0.48
     Januar
    0.47
     Mock
    0.46
     Room
    0.46
     inhibited
    0.46
    POSITIVE LOGITS
    枯
    0.49
    国の
    0.47
     советы
    0.43
    ム
    0.42
    幼
    0.42
    சி
    0.41
    nesses
    0.41
    ่ย
    0.41
    к
    0.41
    国家
    0.40
    Activations Density 0.001%

    No Known Activations