© 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. 130794
    Prev
    Next
    INDEX
    Explanations

    shipping and procedures

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

    potential obstructions, why, and another

    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
     colourful
    0.48
     flavoured
    0.46
     Sólo
    0.45
     ກ
    0.43
     Mughal
    0.43
     subdued
    0.43
     Lá
    0.43
     រ
    0.42
     frosted
    0.42
     devoured
    0.42
    POSITIVE LOGITS
    來看
    0.49
    வதன்
    0.48
     collegamento
    0.47
     радика
    0.46
    知らない
    0.46
     όταν
    0.44
    可能有
    0.44
    빱
    0.44
    졀
    0.44
    㯎
    0.44
    Activations Density 0.001%

    No Known Activations