© 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. 123847
    Prev
    Next
    INDEX
    Explanations

    status values and strings

    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
    地點
    0.50
    ਾਕ
    0.50
     Entfer
    0.47
    ogt
    0.46
    ripciones
    0.45
    铉
    0.44
     Moyen
    0.43
    ocèle
    0.43
    èdent
    0.43
    ensi
    0.42
    POSITIVE LOGITS
    u
    0.45
     houseplants
    0.45
    a
    0.43
    services
    0.43
    :
    0.41
     TICK
    0.40
    :*
    0.40
    sys
    0.39
    у
    0.39
     どう
    0.38
    Activations Density 0.008%

    No Known Activations