© 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. 8763
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
    hensive
    0.52
    Dollars
    0.52
    weekly
    0.50
     लिविंग
    0.50
    FirstName
    0.49
    Corruption
    0.49
     잔
    0.48
    GLASS
    0.48
    Sixth
    0.47
    Fols
    0.47
    POSITIVE LOGITS
     OUR
    0.50
     Jak
    0.47
     sym
    0.46
     Ü
    0.46
     UNE
    0.46
     grandma
    0.45
     realised
    0.45
     utilised
    0.44
     schwar
    0.44
     derive
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.