© 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. 46274
    Prev
    Next
    INDEX
    Explanations

    line of duty, job, service

    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
     cosas
    0.69
     coisas
    0.65
     deixe
    0.64
     păr
    0.63
     apparaître
    0.62
     toneladas
    0.60
     graus
    0.60
    시
    0.59
     respectivamente
    0.58
     éventuellement
    0.58
    POSITIVE LOGITS
    ars
    0.69
    ir
    0.68
    at
    0.68
    is
    0.67
    an
    0.62
    as
    0.62
    n
    0.57
    are
    0.57
    ath
    0.56
    uk
    0.55
    Activations Density 0.001%

    No Known Activations