© 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. 8888
    Prev
    Next
    INDEX
    Explanations

    control group

    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
     realmente
    0.68
     estará
    0.62
    ,”
    0.61
    …”
    0.60
    能夠
    0.59
    .”
    0.58
     genera
    0.58
     è
    0.57
    ”.
    0.57
    ...”
    0.56
    POSITIVE LOGITS
    დის
    0.76
    ਟ
    0.64
    jobs
    0.63
    vegetarian
    0.62
    w
    0.62
    ົາ
    0.61
    dys
    0.61
    controls
    0.60
     કરીએ
    0.60
    european
    0.60
    Activations Density 0.003%

    No Known Activations