© 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. 31-GEMMASCOPE-2-RES-262K
    7. 35020
    Prev
    Next
    INDEX
    Explanations

    details about data, problems, or requests

    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
    тного
    0.46
    ढ़ाई
    0.42
    Chemical
    0.42
    revenue
    0.42
    सर्व
    0.42
     estábamos
    0.42
    мир
    0.42
    י
    0.41
    зовая
    0.41
    Quant
    0.41
    POSITIVE LOGITS
    ılır
    0.49
    aria
    0.47
     flapping
    0.46
    ılan
    0.46
     Floret
    0.46
     Cala
    0.46
     Flo
    0.45
    akah
    0.45
    (#
    0.44
    azaki
    0.44
    Activations Density 0.001%

    No Known Activations