© 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. 52184
    Prev
    Next
    INDEX
    Explanations

    device drivers

    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
    라
    0.47
    nante
    0.43
    诚信
    0.42
     Ve
    0.41
     GH
    0.41
    㿟
    0.40
    دارة
    0.39
     Discharge
    0.39
     Exclusion
    0.39
    鳎
    0.39
    POSITIVE LOGITS
     amplify
    0.50
    Quelle
    0.49
     helps
    0.47
     toa
    0.47
     enables
    0.47
     compares
    0.46
     expand
    0.46
     to
    0.46
     attracts
    0.44
     answer
    0.44
    Activations Density 0.002%

    No Known Activations