© 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. 4974
    Prev
    Next
    INDEX
    Explanations

    lists and structured text

    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
    rinsic
    1.63
    7
    1.56
    6
    1.28
    8
    1.20
     opin
    1.16
    ▉
    1.16
    9
    1.14
    5
    1.14
    ▋
    1.13
    끽
    1.12
    POSITIVE LOGITS
     organised
    2.01
     feasts
    1.90
     organiser
    1.89
    (=
    1.89
     arrows
    1.89
    organiser
    1.88
    organised
    1.87
     organisation
    1.85
     (£
    1.85
     schedules
    1.83
    Activations Density 0.009%

    No Known Activations