© 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. 126079
    Prev
    Next
    INDEX
    Explanations

    metal genre

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

    changing parameters

    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
    (
    0.54
    মুখ
    0.50
     pommes
    0.50
    (“
    0.48
     formules
    0.46
    ای
    0.46
    absch
    0.45
     appe
    0.45
     états
    0.45
    '
    0.45
    POSITIVE LOGITS
     गड़ब
    0.51
     خراب
    0.49
     కాల్
    0.47
     PICK
    0.47
     टेक
    0.47
     тря
    0.46
    пин
    0.46
     क्रा
    0.46
    }"]
    0.46
    り返
    0.46
    Activations Density 0.000%

    No Known Activations