© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3965
    Prev
    Next
    INDEX
    Explanations

    leading provider

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    ultima
    1.63
    谬
    1.60
    )^{-
    1.50
    })^{-
    1.48
     older
    1.46
    などで
    1.41
     chronology
    1.40
    轶
    1.40
    等等
    1.40
     corrections
    1.38
    POSITIVE LOGITS
     Demand
    1.63
    Demand
    1.54
     Perce
    1.53
    먼
    1.51
     Sensing
    1.51
    Shared
    1.48
    Germain
    1.47
    Processing
    1.44
    Merchant
    1.43
     Creating
    1.41
    Activations Density 0.051%

    No Known Activations