© 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. 111286
    Prev
    Next
    INDEX
    Explanations

    allergens and species

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

    distance, measurements, possibilities, known entities

    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
    ቫ
    0.51
    ній
    0.50
     메소
    0.50
    ጳ
    0.50
     invokes
    0.50
    ুদ্ধে
    0.49
    ドア
    0.49
     advogado
    0.49
     شرطونو
    0.48
     recommand
    0.48
    POSITIVE LOGITS
    he
    0.48
     Theme
    0.46
    الس
    0.45
    mill
    0.44
    Assim
    0.44
    1
    0.43
    issue
    0.43
    SL
    0.42
     Ship
    0.42
    atico
    0.42
    Activations Density 0.000%

    No Known Activations