© 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. 59219
    Prev
    Next
    INDEX
    Explanations

    because most or 2

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

    technical descriptions and terminology

    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
     microarray
    0.45
     whom
    0.45
    কা
    0.44
     outskirts
    0.42
     likes
    0.42
    .*;
    0.41
    ್
    0.41
    '.
    0.41
     denies
    0.41
    Check
    0.41
    POSITIVE LOGITS
     entusias
    0.57
     tensione
    0.52
     brindar
    0.50
     impulso
    0.49
    ‶
    0.48
     entusiasmo
    0.47
     arrivent
    0.46
    钢
    0.46
     otomatik
    0.45
     piden
    0.45
    Activations Density 0.000%

    No Known Activations