© 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. 147806
    Prev
    Next
    INDEX
    Explanations

    languages and special characters

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

    guidelines, considerations, requirements

    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
     ។
    0.51
    ités
    0.46
    assara
    0.46
     বিহার
    0.46
     niente
    0.46
     lleg
    0.44
     ventricular
    0.44
     ステ
    0.44
     moderately
    0.44
     cominc
    0.44
    POSITIVE LOGITS
    禁止
    0.45
    ת
    0.44
    थित
    0.43
    氤
    0.43
    噘
    0.42
    प्प
    0.42
    芊
    0.41
    ্তার
    0.41
    罗
    0.41
    writeValue
    0.41
    Activations Density 0.000%

    No Known Activations