© 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. 53125
    Prev
    Next
    INDEX
    Explanations

    Reservations

    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
    ö
    0.44
     Guilty
    0.39
    сами
    0.39
    ทร
    0.38
    Dramatic
    0.38
     Швейца
    0.38
    Reduced
    0.38
    ధీ
    0.37
    ґ
    0.37
    债务
    0.37
    POSITIVE LOGITS
    hstack
    0.46
    kosť
    0.45
     scaffolds
    0.40
    ඤ
    0.40
    inje
    0.39
     경우가
    0.39
     సందర్భ
    0.38
     derog
    0.38
    nu
    0.38
     prosthesis
    0.38
    Activations Density 0.000%

    No Known Activations