© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10632
    Prev
    Next
    INDEX
    Explanations

    hitting key points

    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_40_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
     tranh
    0.46
     Thorough
    0.45
     gestalten
    0.44
    壑
    0.41
     disput
    0.39
     hâ
    0.39
     avaliar
    0.39
     Mouth
    0.38
     Artwork
    0.38
    ാനം
    0.38
    POSITIVE LOGITS
     hitting
    0.68
     snooze
    0.68
     hit
    0.68
    hitting
    0.59
    擊
    0.59
    Hitting
    0.57
     HIT
    0.54
     jackpot
    0.54
     hard
    0.52
    击
    0.52
    Activations Density 0.104%

    No Known Activations