© 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-65K
    7. 2670
    Prev
    Next
    INDEX
    Explanations

    Generate story prompts

    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_65k_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
     for
    0.57
    als
    0.46
    గా
    0.45
    دين
    0.44
    బ్బు
    0.44
    addy
    0.43
     digesting
    0.42
    Z
    0.42
    ura
    0.42
    RA
    0.42
    POSITIVE LOGITS
     umo
    0.63
     uruch
    0.57
     tavolo
    0.57
     wilayah
    0.52
     kua
    0.52
    เผย
    0.52
    絶対に
    0.52
    ми
    0.51
    popupTheme
    0.50
     auricular
    0.50
    Activations Density 0.000%

    No Known Activations