© 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. 38637
    Prev
    Next
    INDEX
    Explanations

    emails and accounts

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

    categorization and sequencing

    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
    今回は
    0.50
    ﺷ
    0.50
     todas
    0.46
     Tick
    0.45
     cifras
    0.44
     mira
    0.42
     exons
    0.42
    կ
    0.42
     lados
    0.42
     TIMES
    0.42
    POSITIVE LOGITS
    Language
    0.44
    SignUp
    0.43
    Shelf
    0.42
    Stable
    0.42
    Year
    0.42
    Library
    0.40
    Mother
    0.40
    Medicine
    0.40
    E
    0.40
    Depth
    0.40
    Activations Density 0.000%

    No Known Activations