© 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. 219836
    Prev
    Next
    INDEX
    Explanations

    embroided logo and typography

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

    lists, punctuation, and Travel

    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
     |”
    0.44
     ایمان
    0.43
    Buenas
    0.42
    muy
    0.42
    rror
    0.41
    tMap
    0.40
     Hancock
    0.40
    ibrate
    0.39
    ഭ്യാസ
    0.39
    tudo
    0.39
    POSITIVE LOGITS
    wast
    0.50
     deferred
    0.50
     社
    0.48
     feta
    0.47
     стаў
    0.45
     Deferred
    0.45
    ิว
    0.45
     liga
    0.45
    Deferred
    0.45
     sawdust
    0.45
    Activations Density 0.000%

    No Known Activations