© 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. 175703
    Prev
    Next
    INDEX
    Explanations

    book or publication information

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

    the range of human expression

    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
    ᇂ
    0.49
     accueillir
    0.48
     अध्यक्ष
    0.47
     δύο
    0.45
     synthesize
    0.45
    }_{+}
    0.45
     πολλά
    0.44
     δεύτε
    0.44
     cinqui
    0.43
     ಅಧ್ಯ
    0.43
    POSITIVE LOGITS
    Prayer
    0.46
     returned
    0.46
     ডিপ
    0.45
    Response
    0.44
    Произ
    0.44
    Converter
    0.44
     Prayer
    0.44
    Су
    0.44
    ("**
    0.44
    ोरी
    0.43
    Activations Density 0.001%

    No Known Activations