© 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. 145277
    Prev
    Next
    INDEX
    Explanations

    punctuation and non-English characters

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

    action or consequence

    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
    EN
    0.44
    ಿ
    0.43
    itha
    0.42
    3
    0.42
    AIN
    0.42
    現代
    0.41
    lina
    0.40
    THER
    0.40
    נ
    0.40
    kita
    0.39
    POSITIVE LOGITS
     注意
    0.51
     圆
    0.50
     因为
    0.49
    。”
    0.49
     Để
    0.48
     Phạm
    0.48
     ★★
    0.48
     这是
    0.48
    ίου
    0.47
     ప్రారంభ
    0.47
    Activations Density 0.000%

    No Known Activations