© 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. 5191
    Prev
    Next
    INDEX
    Explanations

    implementation of architecture

    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
    .
    1.93
    。
    1.67
    ।
    1.55
    ;
    1.51
    .;
    1.20
    .*
    1.17
    ։
    1.16
    !
    1.06
    。(
    1.03
     Other
    1.02
    POSITIVE LOGITS
    部は
    3.73
     emits
    3.73
    性は
    3.67
    率は
    3.66
    氏は
    3.64
     possesses
    3.62
     equates
    3.61
    스는
    3.59
    상은
    3.58
     corresponds
    3.57
    Activations Density 0.263%

    No Known Activations