© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 4491
    Prev
    Next
    INDEX
    Explanations

    user-friendly interface

    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
    m
    0.86
    тите
    0.82
    F
    0.75
    mäßig
    0.73
    ,
    0.73
    Service
    0.71
     on
    0.70
    }$,
    0.70
    ー
    0.70
    ล
    0.70
    POSITIVE LOGITS
    á
    0.98
    friendly
    0.88
    ین
    0.84
    ک
    0.81
    िड
    0.80
     friendliness
    0.79
    il
    0.75
     diversos
    0.75
     vuel
    0.74
     ۴
    0.72
    Activations Density 0.005%

    No Known Activations