© 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. 236144
    Prev
    Next
    INDEX
    Explanations

    melodies ranc

    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
     exámenes
    0.52
     ecuaciones
    0.49
     campsites
    0.49
    ,<
    0.47
     engines
    0.47
     dispositivos
    0.47
     intest
    0.46
     उपयोग
    0.46
     języ
    0.46
     usos
    0.46
    POSITIVE LOGITS
    غه
    0.42
    idine
    0.42
    iddag
    0.42
    ила
    0.42
    azu
    0.41
    。
    0.40
     kor
    0.40
    laublich
    0.40
     Ran
    0.39
    Ба
    0.39
    Activations Density 0.006%

    No Known Activations