© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3392
    Prev
    Next
    INDEX
    Explanations

    specific identifiers often followed by delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (
    0.81
     ہوگا۔
    0.80
    ငံ
    0.79
     होगा
    0.77
    on
    0.76
     आएगा
    0.73
     όλα
    0.73
    䍜
    0.71
     уди
    0.70
    িব
    0.69
    POSITIVE LOGITS
    :
    1.30
    ;
    1.25
    #
    0.93
    %
    0.91
    3
    0.87
    "
    0.85
    ৩
    0.85
    ?
    0.81
    9
    0.79
    <0x91>
    0.78
    Activations Density 0.000%

    No Known Activations