© 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. 201617
    Prev
    Next
    INDEX
    Explanations

    identify roles vs events

    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
    ificance
    0.46
    iline
    0.43
    otiv
    0.42
    ielten
    0.42
    éd
    0.41
    ull
    0.41
    ┊
    0.41
    uls
    0.40
    钿
    0.40
    ikti
    0.40
    POSITIVE LOGITS
     DIO
    0.39
    انية
    0.39
    ファー
    0.39
    سے
    0.38
    ಡ್
    0.37
     préparation
    0.37
     cosidd
    0.36
    ディア
    0.36
     COVID
    0.36
     RBD
    0.36
    Activations Density 0.002%

    No Known Activations