© 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. 22049
    Prev
    Next
    INDEX
    Explanations

    JSON structure and severity

    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
    拁
    0.53
     hurting
    0.48
     Curl
    0.47
     hurts
    0.46
     Worse
    0.46
    第壹百
    0.43
     জার্সি
    0.42
    اسة
    0.42
     Myles
    0.42
     Hurts
    0.42
    POSITIVE LOGITS
     topologically
    0.43
     graphically
    0.42
    u
    0.42
    ivamente
    0.42
    zel
    0.40
    敏
    0.39
    ut
    0.39
    зи
    0.38
    quasi
    0.38
    ζ
    0.38
    Activations Density 0.001%

    No Known Activations