© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 119530
    Prev
    Next
    INDEX
    Explanations

    screen projection and raycasting

    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
    さて
    0.39
    욧
    0.38
    estab
    0.38
     دام
    0.38
    Ix
    0.37
    癮
    0.37
     sö
    0.36
    idam
    0.36
    alahkan
    0.36
    딱
    0.36
    POSITIVE LOGITS
    Screen
    0.72
     screen
    0.72
     Screen
    0.72
    屏幕
    0.66
    screen
    0.63
     screens
    0.58
    屏
    0.57
     Bildschirm
    0.55
    screens
    0.54
     SCREEN
    0.54
    Activations Density 0.001%

    No Known Activations