© 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. 25254
    Prev
    Next
    INDEX
    Explanations

    Swedish/Danish question words

    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
    y
    0.69
    i
    0.63
    u
    0.62
    k
    0.62
    -
    0.61
    an
    0.59
    e
    0.58
    est
    0.57
    o
    0.55
    ia
    0.55
    POSITIVE LOGITS
    Hvis
    0.67
    蛜
    0.61
     når
    0.59
    Så
    0.58
    BlockUsed
    0.57
    engelsk
    0.56
    ologisk
    0.55
     hjæl
    0.54
     hvor
    0.53
     forskellige
    0.53
    Activations Density 0.008%

    No Known Activations