© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 210421
    Prev
    Next
    INDEX
    Explanations

    collocations or compound word completions

    np_acts-logits-general · gemini-2.5-flash-lite

    storytelling and continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    4
    0.64
    3
    0.63
    7
    0.61
    5
    0.58
    2
    0.57
    z
    0.57
    8
    0.57
    6
    0.56
    Methyl
    0.53
    1
    0.50
    POSITIVE LOGITS
     Catherine
    0.58
     Persians
    0.56
     Cavan
    0.55
     storyteller
    0.55
     Afghans
    0.54
     Kxh
    0.54
     Tshirt
    0.54
     Aztecs
    0.53
     Journalism
    0.52
     saddened
    0.52
    Activations Density 0.000%

    No Known Activations