© 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. 3188
    Prev
    Next
    INDEX
    Explanations

    before questions

    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
    I
    0.38
    ني
    0.37
    4
    0.37
    *.
    0.37
    ഷ്ട്ര
    0.37
     =
    0.35
    ILE
    0.34
    <
    0.34
    .’
    0.33
    
    0.33
    POSITIVE LOGITS
    as
    0.53
    at
    0.47
    ل
    0.41
    and
    0.39
    an
    0.39
    this
    0.38
    ान
    0.36
    icolo
    0.36
    л
    0.36
     utilisons
    0.36
    Activations Density 1.430%

    No Known Activations