© 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. 55235
    Prev
    Next
    INDEX
    Explanations

    shower, rain, snow

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

    parenthetical stage directions

    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
    н
    0.47
     অধিকাংশই
    0.43
    ド
    0.43
    м
    0.42
    d
    0.41
     есть
    0.41
    стить
    0.40
    لب
    0.40
    勝
    0.40
    дор
    0.40
    POSITIVE LOGITS
    的发展
    0.50
     Sheffield
    0.48
     जेव्हा
    0.46
     présentent
    0.45
     surprises
    0.44
    woł
    0.44
     manière
    0.43
    劦
    0.43
    曾经
    0.43
     Mannes
    0.43
    Activations Density 0.000%

    No Known Activations