© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200241
    Prev
    Next
    INDEX
    Explanations

    like-for-like basis, confident swim

    np_acts-logits-general · gemini-2.5-flash-lite

    concepts, lists, string, three, worry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATIONS
    0.54
    icletas
    0.53
    heme
    0.52
    hetto
    0.52
    ToArabic
    0.51
    ᆯ
    0.49
    タイプ
    0.49
    (){}
    0.48
    ವಿಲ್ಲ
    0.47
    ounded
    0.47
    POSITIVE LOGITS
     gând
    0.48
     concept
    0.47
     cuestión
    0.45
    blom
    0.42
    ﻮ
    0.41
     soi
    0.40
     avendo
    0.40
     đối
    0.40
     ваших
    0.40
    心が
    0.40
    Activations Density 0.001%

    No Known Activations