© 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. 25142
    Prev
    Next
    INDEX
    Explanations

    objects *based on the subtle changes

    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
    т
    0.60
    त
    0.53
     иногда
    0.52
    ч
    0.50
     взгля
    0.49
    Tickets
    0.48
     затра
    0.47
    л
    0.47
    й
    0.47
    си
    0.46
    POSITIVE LOGITS
     upregulated
    0.56
     coated
    0.54
     detecting
    0.53
     chemically
    0.52
     zebrafish
    0.51
     neutrophil
    0.51
     yeast
    0.51
     directly
    0.50
     sunscreen
    0.50
     contiguous
    0.50
    Activations Density 0.004%

    No Known Activations