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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101028
    Prev
    Next
    INDEX
    Explanations

    German, French, Spanish, Portuguese, Italian, Russian

    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
     Directive
    0.46
    В
    0.46
     blank
    0.46
    А
    0.45
     directive
    0.44
     Video
    0.43
    În
    0.43
     tiny
    0.42
    На
    0.42
    </h2>
    0.42
    POSITIVE LOGITS
     campañas
    0.51
     senhores
    0.49
     kroner
    0.48
     하였다
    0.46
     temporadas
    0.46
     kraj
    0.45
    하였다
    0.45
    ്ലാ
    0.45
     república
    0.44
     بالس
    0.43
    Activations Density 0.006%

    No Known Activations