© 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. 31708
    Prev
    Next
    INDEX
    Explanations

    ice cream

    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
    ur
    1.16
    ר
    0.99
    ut
    0.97
    ור
    0.96
    ל
    0.91
    ار
    0.89
    at
    0.88
    5
    0.88
    ir
    0.87
    il
    0.86
    POSITIVE LOGITS
    ف
    0.95
     tämän
    0.88
     parâ
    0.73
     магази
    0.71
     และ
    0.71
     và
    0.71
    )。
    0.71
    nya
    0.69
     був
    0.69
    ів
    0.69
    Activations Density 0.005%

    No Known Activations