© 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. 116834
    Prev
    Next
    INDEX
    Explanations

    technical abbreviations

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

    protocols, data formats, connections

    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
    ීම
    0.51
     disgraceful
    0.49
     אשר
    0.48
    クリル
    0.48
    ﺏ
    0.47
    дің
    0.46
     וח
    0.46
     ማለት
    0.46
    
    0.45
    感じる
    0.45
    POSITIVE LOGITS
    to
    0.63
     parser
    0.53
     Är
    0.48
    ToObject
    0.48
    To
    0.47
    öy
    0.47
    格式
    0.46
    佽
    0.46
    on
    0.46
    ToJava
    0.46
    Activations Density 0.159%

    No Known Activations