© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 143977
    Prev
    Next
    INDEX
    Explanations

    file extensions like .js, .ts

    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
    ið
    0.52
    this
    0.50
    áver
    0.49
    rmse
    0.47
    oms
    0.46
    OU
    0.45
    मेरा
    0.44
     ဗ
    0.44
    ពិសេស
    0.44
    ⓜ
    0.44
    POSITIVE LOGITS
    生涯
    0.44
     Schatz
    0.43
    чее
    0.41
    adone
    0.41
     Schultz
    0.41
     shaved
    0.40
    **,
    0.39
     scooped
    0.39
     suisse
    0.39
    ***
    0.39
    Activations Density 0.009%

    No Known Activations