© 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. 121546
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

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

    Fuzzy Matching

    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
    jedno
    0.54
    }){
    0.50
    values
    0.49
     комі
    0.48
     deği
    0.48
     পৌর
    0.47
    }
    0.47
     লেখক
    0.47
     бир
    0.47
     অঙ্
    0.47
    POSITIVE LOGITS
    ８
    0.54
     Freestyle
    0.51
    8
    0.50
     Skin
    0.46
     restrooms
    0.43
     GBM
    0.42
     Silva
    0.42
    ériel
    0.41
    லம்
    0.40
    ونا
    0.40
    Activations Density 0.001%

    No Known Activations