© 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. 106064
    Prev
    Next
    INDEX
    Explanations

    dark plumage

    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
    ра
    0.83
    ের
    0.66
    j
    0.64
     traceable
    0.62
    ва
    0.61
     pembayaran
    0.59
     Сим
    0.59
    ವಾಗಿರುತ್ತದೆ
    0.59
    𝓐
    0.57
    হার
    0.56
    POSITIVE LOGITS
    TE
    0.80
     ört
    0.74
    لك
    0.71
    LE
    0.70
    CO
    0.70
    KE
    0.70
     arteries
    0.68
    KU
    0.67
    る
    0.67
    CT
    0.66
    Activations Density 0.000%

    No Known Activations