© 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. 70469
    Prev
    Next
    INDEX
    Explanations

    first-time

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

    novel, creative, critical, makeup, reporting

    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
    でしたが
    0.46
     Фі
    0.46
     बालो
    0.45
    odd
    0.44
    ený
    0.44
    ロ
    0.44
    ená
    0.43
    𝓐
    0.43
    Ĭ
    0.43
    textured
    0.43
    POSITIVE LOGITS
     hak
    0.48
     kunci
    0.47
    tasks
    0.47
    ונים
    0.46
     ears
    0.45
    น
    0.45
     booths
    0.44
     tasks
    0.44
    力和
    0.44
     অর্থাৎ
    0.43
    Activations Density 0.000%

    No Known Activations