© 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. 23524
    Prev
    Next
    INDEX
    Explanations

    braking, linker

    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
    movement
    0.39
    ဆောင်
    0.38
    isser
    0.38
     dí
    0.38
     लीवर
    0.38
    🚜
    0.38
    Ĵ
    0.36
     dilaksanakan
    0.36
    施
    0.35
    ^{+
    0.34
    POSITIVE LOGITS
     visual
    0.43
    Visual
    0.43
     visually
    0.42
    干净
    0.41
    未经
    0.41
     opportunity
    0.41
     визуа
    0.41
     Damit
    0.37
     બનાવે
    0.36
     возможность
    0.35
    Activations Density 0.000%

    No Known Activations