© 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. 96493
    Prev
    Next
    INDEX
    Explanations

    horoscopes targeting personal advice

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

    compile, muscles, accept, Period, Crick, Legislation, llama

    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
    उन्
    0.46
    s
    0.46
    m
    0.46
    h
    0.45
    p
    0.44
    ed
    0.44
    by
    0.44
     entered
    0.42
     Spain
    0.42
    c
    0.42
    POSITIVE LOGITS
     músc
    0.49
     نسخ
    0.49
     كلام
    0.47
     muscul
    0.46
     Muscles
    0.44
     músculos
    0.44
     دستور
    0.44
     conjunta
    0.44
    Muscle
    0.43
    زى
    0.43
    Activations Density 0.001%

    No Known Activations