© 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. 31-GEMMASCOPE-2-RES-262K
    7. 90642
    Prev
    Next
    INDEX
    Explanations

    what happens first

    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
    ੨
    0.48
     ஆசிரியர்
    0.46
    。",
    0.45
     Republican
    0.43
    othèque
    0.43
     JsonConvert
    0.42
    ä
    0.41
     クラ
    0.41
    макраты
    0.41
     刺繍
    0.40
    POSITIVE LOGITS
    OLYBD
    0.55
     spongy
    0.49
    во
    0.48
     muque
    0.47
     filets
    0.47
     muc
    0.46
    у
    0.45
     scrubbing
    0.44
     exfoli
    0.44
     obese
    0.44
    Activations Density 0.004%

    No Known Activations