© 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. 104643
    Prev
    Next
    INDEX
    Explanations

    clarinet, company, members

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

    oddly satisfying

    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
     prá
    0.47
     stro
    0.43
     Frankfort
    0.42
    o
    0.42
     Stro
    0.42
     Targ
    0.42
     Heraus
    0.41
    Мо
    0.41
    }>{
    0.40
     ترتيب
    0.39
    POSITIVE LOGITS
     બાળ
    0.53
    ∂
    0.47
    വിട
    0.46
     ⚫
    0.45
    のお店
    0.45
    🔥
    0.44
    ！）
    0.43
     इंसान
    0.43
     cháy
    0.42
    tted
    0.42
    Activations Density 0.001%

    No Known Activations