© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5036
    Prev
    Next
    INDEX
    Explanations

    user/model interaction continuation

    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
    Negative Logits
     Niko
    1.82
    9
    1.82
    Freedom
    1.81
    freedom
    1.77
     novoProduto
    1.74
    7
    1.73
    承認
    1.73
     tundra
    1.71
     있어야
    1.70
    wesen
    1.70
    POSITIVE LOGITS
     algorithms
    1.13
     algorithm
    1.06
     leaks
    0.95
     historians
    0.95
     ripples
    0.93
     biases
    0.91
     indexes
    0.90
     optimizer
    0.90
     spreads
    0.90
     (£
    0.88
    Activations Density 0.026%

    No Known Activations