© 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. 44751
    Prev
    Next
    INDEX
    Explanations

    specific word sequences

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

    specific issue or capability

    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
    nje
    0.48
    뷊
    0.48
     مدير
    0.47
     peintre
    0.46
     كتابه
    0.46
     نقص
    0.45
     peint
    0.45
     Veron
    0.45
    ποίη
    0.45
    ప్పటి
    0.45
    POSITIVE LOGITS
    erase
    0.55
    fuel
    0.44
    ว
    0.44
     pats
    0.43
     testim
    0.42
    STORAGE
    0.42
     в
    0.42
    balanced
    0.42
    glide
    0.42
    もない
    0.42
    Activations Density 0.001%

    No Known Activations