© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14859
    Prev
    Next
    INDEX
    Explanations

    office hours and availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    ATT
    0.71
    Proc
    0.70
     execution
    0.70
     jednost
    0.69
    raul
    0.68
    発
    0.68
     brutality
    0.68
     beautiful
    0.67
    क्राम
    0.66
     కో
    0.65
    POSITIVE LOGITS
     balsamic
    0.86
     họp
    0.80
     ValidationError
    0.79
     fainting
    0.77
     abhiv
    0.77
    ⅜
    0.77
     көп
    0.77
     thuring
    0.76
     aldehyde
    0.75
     konstit
    0.75
    Activations Density 0.008%

    No Known Activations