© 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. 126193
    Prev
    Next
    INDEX
    Explanations

    different choices and options

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

    evidence, shield, facing, dictionary, Who

    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
    ロゴ
    0.53
     sûr
    0.50
    Những
    0.49
     imbued
    0.48
    പ
    0.47
     piccole
    0.47
     marquées
    0.46
     conscientes
    0.46
     небольшой
    0.46
     લાખ
    0.46
    POSITIVE LOGITS
    \
    0.47
     Evidence
    0.46
     aer
    0.46
    </h2>
    0.46
     mirror
    0.45
    komst
    0.45
     “
    0.44
     ion
    0.44
     or
    0.43
    >
    0.43
    Activations Density 0.002%

    No Known Activations