© 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. 49467
    Prev
    Next
    INDEX
    Explanations

    pointer * int bool

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

    programming operations and types

    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
    gono
    0.43
    pé
    0.43
    angulo
    0.43
    rono
    0.42
    <unused1097>
    0.42
    في
    0.42
    prosperity
    0.41
    <unused1007>
    0.41
    telling
    0.41
    คองโก
    0.41
    POSITIVE LOGITS
     get
    0.64
     getDefault
    0.64
    get
    0.53
     execute
    0.50
     getCurrent
    0.50
     getConnection
    0.49
     getMain
    0.49
     getRandom
    0.48
     getLast
    0.48
     getState
    0.46
    Activations Density 0.000%

    No Known Activations