© 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. 148002
    Prev
    Next
    INDEX
    Explanations

    colors and concepts

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

    specific contexts and conditions

    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
    qst
    0.49
    towards
    0.46
     向
    0.45
    ur
    0.44
    FAST
    0.44
     unmittelbar
    0.44
    at
    0.44
    preis
    0.44
    馬上
    0.44
    IDI
    0.44
    POSITIVE LOGITS
    ⛵
    0.52
     Есть
    0.47
     modList
    0.47
     моря
    0.47
     ferries
    0.47
     beerCount
    0.47
     fratern
    0.46
     Discuss
    0.45
     foie
    0.45
     جذر
    0.45
    Activations Density 0.002%

    No Known Activations