© 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. 9267
    Prev
    Next
    INDEX
    Explanations

    history sections

    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
    is
    0.45
    م
    0.41
    umlahan
    0.40
    𒉰
    0.39
    𝐿
    0.38
    ions
    0.37
     कोणते
    0.37
     چیزی
    0.35
    ivité
    0.34
    晦
    0.34
    POSITIVE LOGITS
     സംഭവ
    0.40
     président
    0.37
     Vigo
    0.35
    సాగ
    0.35
     klub
    0.35
     lainnya
    0.34
     intensa
    0.34
     approfond
    0.34
     klubu
    0.34
     podczas
    0.34
    Activations Density 0.004%

    No Known Activations