© 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. 4925
    Prev
    Next
    INDEX
    Explanations

    <start_of_turn> sequences

    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
     covariate
    1.23
     eyebrows
    1.21
    Ending
    1.18
     usern
    1.16
     adipose
    1.14
     thighs
    1.13
    ।)
    1.13
     ![](
    1.11
    /)
    1.11
     ude
    1.11
    POSITIVE LOGITS
    1
    1.36
     few
    1.27
    list
    1.16
    几次
    1.14
    steps
    1.12
    block
    1.10
     most
    1.10
    ریف
    1.08
    anken
    1.06
    führ
    1.05
    Activations Density 0.025%

    No Known Activations