© 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. 16-GEMMASCOPE-2-RES-262K
    7. 137886
    Prev
    Next
    INDEX
    Explanations

    bank deposits

    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_16_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
    of
    0.81
    ו
    0.75
    u
    0.73
     }
    0.70
     Y
    0.70
    ราย
    0.70
    KES
    0.68
     announc
    0.66
     מ
    0.65
     B
    0.65
    POSITIVE LOGITS
    serif
    0.76
    ulfide
    0.75
     하겠습니다
    0.73
    ime
    0.71
     सामग्री
    0.66
    zenesulf
    0.65
    ensions
    0.65
    ።
    0.64
    ceptions
    0.64
    ωσ
    0.64
    Activations Density 0.001%

    No Known Activations