© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69677
    Prev
    Next
    INDEX
    Explanations

    expressing equivalence or relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    ication
    1.90
     biber
    1.86
    ביר
    1.77
    ğ
    1.75
     contradict
    1.73
     drugiej
    1.71
     deserve
    1.71
    tonic
    1.71
     demolish
    1.71
    ื่น
    1.70
    POSITIVE LOGITS
    pulsewidth
    1.68
     rendement
    1.65
    approximately
    1.59
    \%$
    1.57
    Percentages
    1.52
     Всего
    1.52
     (\$
    1.50
    Jumlah
    1.50
     PROFITS
    1.49
     kWh
    1.49
    Activations Density 0.004%

    No Known Activations