© 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. 30587
    Prev
    Next
    INDEX
    Explanations

    Short, minutes, Alpha

    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
    Requests
    0.46
    ถ
    0.44
    сини
    0.44
    व
    0.43
    ต
    0.43
     vê
    0.43
    道具
    0.43
    ците
    0.42
    ビ
    0.42
    ネイル
    0.42
    POSITIVE LOGITS
     LongNumber
    0.45
     stood
    0.43
     नॉर्म
    0.42
     interoper
    0.42
     GRID
    0.40
    
    0.40
     Kontext
    0.40
     lastName
    0.40
     CommandCenter
    0.40
    attform
    0.40
    Activations Density 0.007%

    No Known Activations