© 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-16K
    7. 2196
    Prev
    Next
    INDEX
    Explanations

    mid middle alignment

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    1
    1.49
    humans
    1.43
    Humans
    1.41
     humans
    1.40
     Ignatius
    1.35
     Humans
    1.26
    ICA
    1.24
    Human
    1.23
    人類
    1.23
     Bons
    1.21
    POSITIVE LOGITS
     cursorPos
    1.08
     rosé
    1.01
    buttonLevel
    1.00
    auce
    0.99
    뉜
    0.99
    ٴ
    0.96
     girly
    0.95
    marginY
    0.95
    ColumnKind
    0.95
     margarine
    0.95
    Activations Density 0.036%

    No Known Activations