© 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. 78033
    Prev
    Next
    INDEX
    Explanations

    last update

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

    discusses sections and technical details

    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
     Bamboo
    0.49
     Mayfield
    0.45
     Schaff
    0.44
    าส
    0.43
     Medications
    0.43
     Done
    0.42
     Bamb
    0.42
    尺
    0.42
    Bamboo
    0.41
    잿
    0.40
    POSITIVE LOGITS
     lanç
    0.58
    ي
    0.57
     consiste
    0.54
     discuss
    0.54
     имеет
    0.54
    a
    0.54
     discusses
    0.52
     sucedió
    0.52
    idlo
    0.51
     explique
    0.51
    Activations Density 0.001%

    No Known Activations