© 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. 41741
    Prev
    Next
    INDEX
    Explanations

    counts, proportions, and examples

    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
     संग्रहण
    0.44
    over
    0.41
    𝙤
    0.40
    in
    0.40
     расстоя
    0.39
    asının
    0.38
    토
    0.38
    𝕒
    0.38
    ")}}'
    0.38
     максимально
    0.38
    POSITIVE LOGITS
     cases
    0.52
     occurrences
    0.42
     patients
    0.41
     Failed
    0.40
     complicaciones
    0.39
     others
    0.38
     complicating
    0.38
     hamil
    0.38
     examples
    0.38
     তবে
    0.38
    Activations Density 0.011%

    No Known Activations