© 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. 175556
    Prev
    Next
    INDEX
    Explanations

    Facebook sharing

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

    after end or understand or point

    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
    楪
    0.55
    模块
    0.51
    楲
    0.51
     sostit
    0.48
    슐
    0.46
     घटक
    0.46
    楧
    0.46
     baar
    0.45
    鲈
    0.45
     куп
    0.45
    POSITIVE LOGITS
    z
    0.53
    u
    0.48
    compart
    0.48
    wj
    0.47
    י
    0.46
    sy
    0.46
     responded
    0.45
    sj
    0.45
    impression
    0.45
    ow
    0.45
    Activations Density 0.001%

    No Known Activations