© 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. 43556
    Prev
    Next
    INDEX
    Explanations

    place names or entities

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

    technical terms and descriptions

    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
     వచ్చ
    0.53
     ବି
    0.49
     भरतपुर
    0.46
    itte
    0.45
     всех
    0.45
    dihydro
    0.45
    yaa
    0.45
    𝗱
    0.44
    Rajasthan
    0.44
    umum
    0.44
    POSITIVE LOGITS
     locomotive
    0.49
     exploiting
    0.46
     cl
    0.45
    лює
    0.45
     prestazioni
    0.42
    א
    0.42
    at
    0.42
    גה
    0.42
    i
    0.41
     lungo
    0.41
    Activations Density 0.000%

    No Known Activations