© 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. 49437
    Prev
    Next
    INDEX
    Explanations

    closing buttons and popups

    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
    אם
    0.76
    കോ
    0.70
    崆
    0.70
    ).
    0.70
     oncoming
    0.69
    ्लो
    0.68
     abode
    0.67
    >
    0.66
    يمكن
    0.66
     Calvary
    0.66
    POSITIVE LOGITS
    et
    1.30
    is
    1.12
    en
    1.09
    il
    0.91
     for
    0.88
    an
    0.86
    ли
    0.84
    un
    0.80
    ai
    0.79
    ре
    0.78
    Activations Density 0.004%

    No Known Activations