© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63775
    Prev
    Next
    INDEX
    Explanations

    :**

    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
     المج
    0.47
    U
    0.46
    plus
    0.46
     دليل
    0.46
    !»
    0.44
    Regist
    0.44
    QS
    0.43
     لما
    0.43
     المجتمع
    0.43
     ceea
    0.42
    POSITIVE LOGITS
    ಿಸಿದ್ದರು
    0.45
     formulating
    0.44
     Investigators
    0.44
     OWL
    0.43
    两人
    0.43
    兄
    0.43
    ಿಸಿದ್ದಾರೆ
    0.43
     পড়েছেন
    0.43
    二人
    0.42
     emailing
    0.42
    Activations Density 0.003%

    No Known Activations