© 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. 5018
    Prev
    Next
    INDEX
    Explanations

    various tasks

    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
    7
    1.79
    irti
    1.74
    4
    1.72
    <unused291>
    1.70
    5
    1.68
    rawberry
    1.68
     iniziare
    1.67
    <unused1687>
    1.67
     representar
    1.67
    IVATE
    1.65
    POSITIVE LOGITS
     historians
    1.76
     tide
    1.71
     schemes
    1.65
     idioms
    1.63
     fans
    1.60
     spelling
    1.59
     method
    1.56
     technique
    1.56
     ophthalm
    1.53
     methods
    1.53
    Activations Density 0.005%

    No Known Activations