© 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. 205136
    Prev
    Next
    INDEX
    Explanations

    thickened CA glue

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

    mathematical and geopolitical entities

    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
     DIN
    0.50
     رہنما
    0.49
     Eau
    0.47
     ITU
    0.47
     .)
    0.46
     Tension
    0.45
     TID
    0.45
     عَ
    0.45
     Auditor
    0.45
     Ekonom
    0.45
    POSITIVE LOGITS
    OKR
    0.54
    র্ক
    0.47
    COND
    0.46
    cientes
    0.45
    HEL
    0.45
    HAR
    0.44
    OCO
    0.44
    ASSOC
    0.43
    ﺲ
    0.43
    KET
    0.42
    Activations Density 0.004%

    No Known Activations