© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53787
    Prev
    Next
    INDEX
    Explanations

    sequences and contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ٿ
    0.55
    Templates
    0.52
     powierzchn
    0.46
    emplate
    0.45
     шабло
    0.45
    模板
    0.44
     archiv
    0.43
     поверхность
    0.43
     templates
    0.42
    Surface
    0.41
    POSITIVE LOGITS
     Ст
    0.40
     Seq
    0.39
     cumpr
    0.38
     Sequencing
    0.38
     Sankt
    0.37
    ᓴ
    0.36
     ترتیب
    0.35
     이전
    0.35
     LaSalle
    0.35
     Brittany
    0.35
    Activations Density 0.003%

    No Known Activations