© 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. 30275
    Prev
    Next
    INDEX
    Explanations

    conditional statements, categories, deadlines

    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
     피
    0.47
     imparts
    0.46
    ﺕ
    0.46
    ير
    0.46
     وإن
    0.45
     أنواع
    0.45
     عن
    0.45
    는
    0.45
    }{
    0.45
    RecordPtr
    0.44
    POSITIVE LOGITS
     Aeros
    0.48
     Mercury
    0.47
     Antib
    0.47
     Madison
    0.46
     King
    0.46
     Fight
    0.46
     KING
    0.45
     Perry
    0.45
     Dep
    0.45
     Purchase
    0.44
    Activations Density 0.008%

    No Known Activations