© 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. 110120
    Prev
    Next
    INDEX
    Explanations

    positive descriptions

    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
     ADMINISTRATION
    0.47
     ಜ
    0.44
     einst
    0.44
     osnov
    0.42
     blitt
    0.42
    പു
    0.42
     oficinas
    0.42
     inefficiency
    0.42
     derel
    0.42
     inefficiencies
    0.41
    POSITIVE LOGITS
     Daddy
    0.48
     đẹp
    0.46
     可愛い
    0.46
    cute
    0.46
    _.
    0.46
     loài
    0.46
    g
    0.45
     họ
    0.45
    ভালো
    0.45
     کدام
    0.45
    Activations Density 0.002%

    No Known Activations