Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 44120
    Prev
    Next
    INDEX
    Explanations

    Monthly Breakdown, DC source, separator

    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_31_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
     vine
    0.44
     nozzle
    0.43
     kö
    0.42
     Straßen
    0.42
     
    0.42
    </a>
    0.41
    ଣ
    0.41
     sein
    0.41
    atak
    0.40
    رسٹ
    0.40
    POSITIVE LOGITS
    parity
    0.61
    би
    0.55
     metų
    0.52
    =-
    0.52
    про
    0.50
    шлось
    0.50
    ла
    0.48
     atividade
    0.48
    autoarima
    0.48
    на
    0.47
    Activations Density 0.000%

    No Known Activations