© 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. 59280
    Prev
    Next
    INDEX
    Explanations

    potential members

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

    writing/creative assistance

    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
    ویی
    0.52
     goc
    0.49
    ๑
    0.49
     terrestre
    0.48
     triang
    0.47
     terp
    0.47
     등이
    0.47
    ᓲ
    0.46
     avevano
    0.46
    न्ने
    0.46
    POSITIVE LOGITS
    ស្រាយ
    0.48
     سرمایہ
    0.41
    鹂
    0.41
     sapply
    0.41
    preneurs
    0.40
    afood
    0.39
    NBC
    0.39
    criptor
    0.39
    总量
    0.39
     رموز
    0.39
    Activations Density 0.000%

    No Known Activations