© 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. 31-GEMMASCOPE-2-RES-65K
    7. 52163
    Prev
    Next
    INDEX
    Explanations

    diagrams, charts, or technical data

    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_31_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
     destaca
    0.39
     Directorate
    0.39
     Planning
    0.38
     Journalists
    0.38
    <start_of_image>
    0.38
     Days
    0.37
    highlight
    0.36
    晞
    0.36
     highlighted
    0.36
    भरा
    0.36
    POSITIVE LOGITS
    图
    0.47
     equipamento
    0.43
     membran
    0.43
     posture
    0.42
    示意
    0.42
     beton
    0.42
     postural
    0.42
    пен
    0.41
     nmea
    0.41
     coseno
    0.41
    Activations Density 0.008%

    No Known Activations