© 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. 29401
    Prev
    Next
    INDEX
    Explanations

    technical domain names

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

    javascript parsers and plugins

    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
    ರದ
    0.38
    When
    0.37
    diversity
    0.36
    Postfix
    0.35
    uffy
    0.34
     ظاہر
    0.34
    闇
    0.34
    ))
    0.34
     additions
    0.34
    检测
    0.34
    POSITIVE LOGITS
    艹
    0.44
    zieh
    0.43
     Bienvenidos
    0.42
    şık
    0.41
     하나님
    0.40
     चित
    0.38
     परफेक्ट
    0.38
     compañeros
    0.38
    ॐ
    0.37
    jaa
    0.37
    Activations Density 0.000%

    No Known Activations