© 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. 40-GEMMASCOPE-2-RES-262K
    7. 192639
    Prev
    Next
    INDEX
    Explanations

    screen.blit

    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_262k_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
     نصف
    0.46
    utra
    0.42
    後半
    0.39
    Half
    0.39
     half
    0.38
    half
    0.38
    半
    0.37
     halves
    0.37
     অর্ধেক
    0.37
     mại
    0.35
    POSITIVE LOGITS
    aniya
    0.46
    0.40
     sincerity
    0.39
    vá
    0.39
     ఎమ్
    0.39
    zoni
    0.39
    ndi
    0.38
     COL
    0.38
    ਰੇ
    0.38
    चेता
    0.38
    Activations Density 0.008%

    No Known Activations