© 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. 125179
    Prev
    Next
    INDEX
    Explanations

    author, Australia, rewrite

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

    visualization and cultures

    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
    磁盘
    0.44
     onClose
    0.43
    няка
    0.42
    اموش
    0.42
    单击
    0.41
    منٹ
    0.41
    मॉडल
    0.41
    樯
    0.41
    LastGen
    0.40
    鲍
    0.40
    POSITIVE LOGITS
    in
    0.52
    1
    0.47
    attrib
    0.47
     AJ
    0.46
     terá
    0.46
     substitu
    0.46
    aj
    0.45
     accep
    0.45
     ztr
    0.44
     til
    0.44
    Activations Density 0.001%

    No Known Activations