© 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. 40-GEMMASCOPE-2-RES-262K
    7. 168315
    Prev
    Next
    INDEX
    Explanations

    social structures and interactions

    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_40_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
    สมัย
    0.40
    iments
    0.39
     ამ
    0.37
    agiarism
    0.37
    idade
    0.37
     mistake
    0.37
    ².
    0.37
     Lung
    0.37
    accommodation
    0.36
    pod
    0.36
    POSITIVE LOGITS
    cemia
    0.38
    Ꮩ
    0.38
    LAND
    0.37
    ರೆ
    0.36
     pulgadas
    0.36
     evolves
    0.35
    കെ
    0.35
    ത്തി
    0.35
     equalize
    0.35
    以外
    0.34
    Activations Density 0.000%

    No Known Activations