© 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. 8364
    Prev
    Next
    INDEX
    Explanations

    immediate or initial state of being

    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
     הת
    0.53
     آثار
    0.52
    ຜະລິດຕະພັນ
    0.51
     متعلقه
    0.50
    ޙ
    0.50
     événements
    0.49
    Desen
    0.49
    薷
    0.49
     המח
    0.48
    洺
    0.48
    POSITIVE LOGITS
    re
    0.61
    ur
    0.51
    il
    0.49
    el
    0.47
     Retail
    0.47
    cgi
    0.46
    am
    0.46
    ad
    0.46
    ul
    0.46
    ou
    0.46
    Activations Density 0.001%

    No Known Activations