© 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. 81529
    Prev
    Next
    INDEX
    Explanations

    before diving into specifics

    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
     philosophies
    0.54
     insign
    0.53
     හෝ
    0.53
     オー
    0.52
    বর্ধ
    0.52
     órg
    0.52
     ');
    0.51
     indígena
    0.50
     científicos
    0.49
     shafts
    0.49
    POSITIVE LOGITS
    ни
    0.48
    ผ
    0.47
    ีย
    0.46
    ended
    0.46
    忙
    0.45
    盡
    0.44
    -
    0.43
    б
    0.41
    流
    0.41
    Cit
    0.40
    Activations Density 0.003%

    No Known Activations