© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3371
    Prev
    Next
    INDEX
    Explanations

    Einstein and Freud definitions

    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_16_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
    -
    0.79
    :
    0.60
    .
    0.57
    (
    0.52
    5
    0.47
    ：
    0.47
    ény
    0.46
    iew
    0.45
     werden
    0.43
    ile
    0.43
    POSITIVE LOGITS
    ກັບ
    0.50
     ಸ್ಥಳ
    0.50
    ل
    0.49
    ariyam
    0.47
    ﻙ
    0.46
     ﺍﻟ
    0.46
     antider
    0.46
     ສຳ
    0.44
    avacanam
    0.44
    akkhanam
    0.44
    Activations Density 0.001%

    No Known Activations