© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61850
    Prev
    Next
    INDEX
    Explanations

    essentially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    竄
    0.46
    '
    0.46
     interag
    0.44
    appendix
    0.42
    Ἀ
    0.42
    tte
    0.42
     Slight
    0.42
    ೯
    0.42
     kres
    0.41
    晝
    0.41
    POSITIVE LOGITS
     who
    0.46
     ҳа
    0.45
     suất
    0.44
     άνθρω
    0.44
     осозна
    0.44
     vật
    0.43
     যারা
    0.41
     woman
    0.41
     хочется
    0.40
     impact
    0.40
    Activations Density 0.026%

    No Known Activations