© 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. 14459
    Prev
    Next
    INDEX
    Explanations

    word roots with suffixes

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

    combining, procedural, automatically, modelling

    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
     Οι
    0.33
    и
    0.33
    ę
    0.32
    The
    0.32
    āra
    0.31
    а
    0.31
     или
    0.30
     혹은
    0.30
    ↵
    0.30
     அல்லது
    0.30
    POSITIVE LOGITS
     shoved
    0.32
     houve
    0.32
     ongel
    0.32
     teníamos
    0.31
     rifi
    0.31
     havde
    0.30
     enormes
    0.30
     addirittura
    0.30
     lesiones
    0.29
     atleta
    0.29
    Activations Density 0.000%

    No Known Activations