© 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. 41-GEMMASCOPE-2-RES-262K
    7. 58128
    Prev
    Next
    INDEX
    Explanations

    Angle, reflection, find

    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_all/layer_41_width_262k_l0_big
    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
     Morse
    0.43
     mor
    0.40
    гова
    0.38
    謖
    0.38
    idents
    0.37
    CSV
    0.35
     shabd
    0.34
    plements
    0.34
     Tamil
    0.34
     notValid
    0.33
    POSITIVE LOGITS
    Angle
    0.46
     Find
    0.43
    Find
    0.43
     work
    0.41
     ángulo
    0.41
    态
    0.41
     appraisals
    0.40
     reflexion
    0.40
     lavoro
    0.40
     reflexión
    0.40
    Activations Density 0.001%

    No Known Activations