© 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. 13922
    Prev
    Next
    INDEX
    Explanations

    offering tribute

    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
     אפ
    0.55
    ０
    0.51
     если
    0.49
    с
    0.48
    ン
    0.46
    porcion
    0.46
    崞
    0.46
     வகை
    0.45
     восстанов
    0.45
     ピ
    0.45
    POSITIVE LOGITS
     salesmen
    0.48
     corporate
    0.47
     arbitr
    0.47
     salespeople
    0.46
     boutiques
    0.46
     sales
    0.45
     outsiders
    0.44
     customers
    0.43
     businesses
    0.43
     SME
    0.43
    Activations Density 0.017%

    No Known Activations