© 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. 65669
    Prev
    Next
    INDEX
    Explanations

    institutions and education

    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
     park
    0.47
     parks
    0.43
    Ｙ
    0.40
    Parks
    0.40
     ContentValues
    0.40
    azo
    0.39
     moved
    0.38
     Parks
    0.38
     박
    0.37
     मेगा
    0.37
    POSITIVE LOGITS
     PoE
    0.49
     profe
    0.42
     заслу
    0.40
    🏫
    0.40
     Straight
    0.39
     institut
    0.39
     Vav
    0.39
     Institution
    0.38
     Institutions
    0.38
     Humanities
    0.38
    Activations Density 0.000%

    No Known Activations