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. 458
    Prev
    Next
    INDEX
    Explanations

    predicting specific sequences

    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
    setMax
    0.41
    NERS
    0.41
    ٨
    0.40
    渇
    0.40
    altra
    0.39
     Committee
    0.39
    jsp
    0.39
    another
    0.39
    ATTR
    0.39
     artistique
    0.39
    POSITIVE LOGITS
     будут
    0.54
    嬙
    0.53
    posição
    0.52
     רו
    0.50
     будет
    0.49
    giraffe
    0.48
     recrut
    0.47
     serão
    0.47
    䉽
    0.46
     அந்த
    0.46
    Activations Density 0.002%

    No Known Activations