© 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-16K
    7. 4798
    Prev
    Next
    INDEX
    Explanations

    eating glowing orbs

    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_16k_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
    ä
    0.54
    w
    0.50
    äs
    0.46
     ângulo
    0.45
    ì
    0.44
    hin
    0.44
    äd
    0.44
     enzim
    0.44
    óta
    0.43
    a
    0.43
    POSITIVE LOGITS
     friendships
    0.48
     بلند
    0.47
     speakers
    0.46
     Messaging
    0.46
     octave
    0.46
     speeches
    0.45
     parochial
    0.45
     egos
    0.45
     sentimental
    0.44
     clavier
    0.44
    Activations Density 0.006%

    No Known Activations