© 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. 143408
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

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

    shapes, patterns, replication, inclusion

    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
    ил
    0.52
    posable
    0.51
    powers
    0.49
    product
    0.46
     condensing
    0.45
    S
    0.45
    8
    0.45
     product
    0.45
    !
    0.45
    vival
    0.44
    POSITIVE LOGITS
     Plusieurs
    0.53
     Eduard
    0.52
     Sarajevo
    0.51
     অপর
    0.50
     세포
    0.49
     पार
    0.49
     Lire
    0.49
     Filippo
    0.49
     Résultats
    0.49
     Mujhe
    0.49
    Activations Density 0.000%

    No Known Activations