© 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-65K
    7. 13535
    Prev
    Next
    INDEX
    Explanations

    instructions, examples, questions

    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_65k_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
     be
    0.37
    ↵
    0.33
    ल्या
    0.30
     despite
    0.30
     berbagai
    0.29
     mailing
    0.29
    odot
    0.29
     populer
    0.28
    তী
    0.28
    ový
    0.28
    POSITIVE LOGITS
    г
    0.39
    روع
    0.39
     אחד
    0.38
    Bald
    0.37
     इकट
    0.36
    悽
    0.36
    Basil
    0.36
    CR
    0.36
    যান
    0.36
     usamos
    0.36
    Activations Density 0.117%

    No Known Activations