© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129202
    Prev
    Next
    INDEX
    Explanations

    risk, growth, temperature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    s
    0.53
    د
    0.52
    Facing
    0.45
    시
    0.43
    Therefore
    0.42
    Secretary
    0.42
     florida
    0.41
    President
    0.40
     FEL
    0.40
     facing
    0.40
    POSITIVE LOGITS
    好
    0.52
    encji
    0.51
    ności
    0.50
     яхшы
    0.50
    mmss
    0.50
    inness
    0.49
     ойной
    0.48
    miques
    0.46
    enni
    0.46
    ką
    0.46
    Activations Density 0.001%

    No Known Activations