© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 1942
    Prev
    Next
    INDEX
    Explanations

    hands speaking voice

    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
    a
    0.54
    ه
    0.47
    д
    0.47
    ༠
    0.46
     challengers
    0.46
    ᱐
    0.45
    အတွက်
    0.44
     monotony
    0.44
    0
    0.44
    where
    0.43
    POSITIVE LOGITS
    </h3>
    0.50
     debajo
    0.48
    手指
    0.48
     be
    0.46
    ной
    0.46
     V
    0.45
     flickering
    0.45
    ántica
    0.44
     fingern
    0.42
     рукой
    0.42
    Activations Density 0.596%

    No Known Activations