© 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. 72324
    Prev
    Next
    INDEX
    Explanations

    scoregoalpartfeetweaknessfever

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

    mathematical expressions and code

    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
     সক্র
    0.55
    aloko
    0.55
    衫
    0.53
    اردوش
    0.52
    jsdel
    0.50
    oszt
    0.48
     ছবিতে
    0.48
    gaben
    0.47
    apayati
    0.47
    tìm
    0.47
    POSITIVE LOGITS
    ↵
    0.49
     !=
    0.45
     Function
    0.44
    Unknown
    0.44
    Part
    0.43
    *
    0.43
    Object
    0.43
    Category
    0.43
    、
    0.43
     Part
    0.43
    Activations Density 0.000%

    No Known Activations