© 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. 106413
    Prev
    Next
    INDEX
    Explanations

    technique, market, creativity

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

    complex, creative text generation

    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
     codewords
    0.54
     codeword
    0.50
    াজি
    0.46
     HOP
    0.45
     adjoining
    0.44
     findings
    0.44
     unión
    0.44
    ーター
    0.44
    ーン
    0.43
    ン
    0.43
    POSITIVE LOGITS
    驷
    0.45
    à
    0.44
    andia
    0.43
    2
    0.43
     creativity
    0.42
    geben
    0.42
    5
    0.42
    estell
    0.42
    人气
    0.41
    ితి
    0.41
    Activations Density 0.001%

    No Known Activations