© 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. 142247
    Prev
    Next
    INDEX
    Explanations

    instructions, names, places

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

    tell story and relationships

    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
    ög
    0.52
    objeto
    0.52
    ā
    0.51
    acceptance
    0.47
    çamento
    0.47
    fixes
    0.46
    īt
    0.45
    对象
    0.44
    ɗ
    0.43
    ának
    0.43
    POSITIVE LOGITS
    న
    0.53
     Chow
    0.52
     Krankheit
    0.51
     Yash
    0.50
     Brooke
    0.50
     Algonquin
    0.50
     Donnie
    0.48
     ജീ
    0.48
     Manning
    0.48
     Shen
    0.48
    Activations Density 0.000%

    No Known Activations