© 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. 208747
    Prev
    Next
    INDEX
    Explanations

    changes are, average of

    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
     Mycobacterium
    0.33
     guérison
    0.31
    疟
    0.31
    avacanam
    0.31
     물질
    0.31
     suppuration
    0.30
     Strept
    0.30
     биологи
    0.30
     pathogenesis
    0.30
    luor
    0.30
    POSITIVE LOGITS
     nifty
    0.45
    ↵
    0.39
     scrolling
    0.36
     fintech
    0.36
     the
    0.35
     classy
    0.34
     Coinbase
    0.34
     groovy
    0.34
     button
    0.34
     chunky
    0.34
    Activations Density 0.000%

    No Known Activations