© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 85378
    Prev
    Next
    INDEX
    Explanations

    pixel clustered

    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
    0.53
    ز
    0.47
    负
    0.47
    مركز
    0.45
     RA
    0.45
    ثل
    0.44
    此
    0.44
     border
    0.44
    إ
    0.43
    in
    0.42
    POSITIVE LOGITS
     നടപ
    0.58
    ądź
    0.58
     ALSO
    0.57
     případ
    0.57
     Idani
    0.56
    を踏
    0.56
     współprac
    0.56
    bė
    0.56
    nje
    0.55
     தண்ட
    0.55
    Activations Density 0.000%

    No Known Activations