© 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. 44336
    Prev
    Next
    INDEX
    Explanations

    after comma

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

    code structure with colon

    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
     رشد
    0.48
    cycline
    0.42
     इद
    0.42
    வுகள்
    0.41
    دار
    0.40
    రువు
    0.40
    !;
    0.40
    इट
    0.39
    }$;
    0.39
    lerdir
    0.39
    POSITIVE LOGITS
     principales
    0.47
     principaux
    0.46
     principais
    0.39
    :
    0.38
    associ
    0.38
    Interface
    0.36
    必須
    0.36
     upfront
    0.36
    EXTRA
    0.36
     monte
    0.36
    Activations Density 0.002%

    No Known Activations