© 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. 9478
    Prev
    Next
    INDEX
    Explanations

    mn-related mathematical or linguistic contexts

    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
    '
    0.99
    k
    0.88
    ’
    0.83
    ’”
    0.79
    𝐇
    0.77
    ak
    0.77
    AG
    0.77
    aVal
    0.76
    endant
    0.75
    ED
    0.75
    POSITIVE LOGITS
     .
    1.02
    на
    0.93
    м
    0.79
     trusty
    0.78
    dır
    0.74
    ,
    0.74
    ین
    0.73
     uncomplicated
    0.73
    h
    0.72
    も
    0.72
    Activations Density 0.000%

    No Known Activations