© 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. 40-GEMMASCOPE-2-RES-262K
    7. 7777
    Prev
    Next
    INDEX
    Explanations

    decoding generated text

    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_40_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
     débit
    0.45
    詃
    0.44
    áz
    0.43
    鉻
    0.42
     déliv
    0.41
     оши
    0.41
     sprem
    0.41
    矩
    0.41
     erwähnt
    0.40
     перво
    0.40
    POSITIVE LOGITS
     दूस
    0.39
    Careers
    0.38
    BuildActionEntry
    0.37
     humanities
    0.37
    ￠
    0.37
     finalized
    0.37
     internships
    0.36
     Campus
    0.36
    Coleman
    0.36
    ত্ম
    0.35
    Activations Density 0.000%

    No Known Activations