© 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. 117681
    Prev
    Next
    INDEX
    Explanations

    fixed-width font, discontinuity

    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
    0.49
     s
    0.48
     Mitigation
    0.47
     مع
    0.46
     Christine
    0.45
     Charles
    0.45
     well
    0.44
    Json
    0.44
     Bef
    0.44
    StateException
    0.43
    POSITIVE LOGITS
    אם
    0.74
     esigen
    0.68
     edhe
    0.66
    נ
    0.62
    ла
    0.61
    룺
    0.60
    endim
    0.58
     can
    0.58
    hattim
    0.58
    ாரு
    0.57
    Activations Density 0.000%

    No Known Activations