© 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. 177792
    Prev
    Next
    INDEX
    Explanations

    specific examples and definitions

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

    different specific patterns

    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
     detainees
    0.43
     detention
    0.42
    用户信息
    0.41
     ब्रि
    0.41
     让
    0.41
     earthen
    0.41
     rehearsals
    0.40
     manipulative
    0.40
     unre
    0.40
     detained
    0.40
    POSITIVE LOGITS
     alebo
    0.54
     görüş
    0.45
    เขียน
    0.45
     nebo
    0.44
    獻
    0.44
    ුණ
    0.44
     veya
    0.44
     என்ற
    0.43
     Phenomena
    0.43
     oppure
    0.43
    Activations Density 0.000%

    No Known Activations