© 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. 29398
    Prev
    Next
    INDEX
    Explanations

    routine and types

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

    novel combinations, improvement, abilities

    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
    ↵
    0.44
    Utils
    0.43
    utils
    0.42
    Wu
    0.42
    otip
    0.42
    H
    0.41
    workout
    0.41
    <0x0D>
    0.40
    know
    0.40
    tmp
    0.40
    POSITIVE LOGITS
    データの
    0.55
    𒁹
    0.48
     específicamente
    0.47
     parámetros
    0.46
    மாகவும்
    0.46
     sebagaimana
    0.45
    についても
    0.45
     escánd
    0.44
     columnas
    0.43
     intensifying
    0.43
    Activations Density 0.000%

    No Known Activations