© 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. 31-GEMMASCOPE-2-RES-262K
    7. 126454
    Prev
    Next
    INDEX
    Explanations

    planning with

    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_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
     bait
    0.45
     roster
    0.43
    ก
    0.43
     climb
    0.43
     rematch
    0.42
     whitelist
    0.41
    分
    0.41
    完成后
    0.41
     bounce
    0.41
     drip
    0.41
    POSITIVE LOGITS
    ।
    0.50
    cumin
    0.48
     Educação
    0.45
     },
    0.44
    。
    0.44
    💌
    0.44
    <unused557>
    0.44
     преподава
    0.43
    ORIA
    0.43
     pendidikan
    0.43
    Activations Density 0.001%

    No Known Activations