© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47375
    Prev
    Next
    INDEX
    Explanations

    objects or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرغم
    -0.76
    mLast
    -0.74
    Libros
    -0.73
    Kore
    -0.71
     sher
    -0.69
    Escrito
    -0.69
    Contras
    -0.69
     💕
    -0.68
    oyle
    -0.68
    ucle
    -0.68
    POSITIVE LOGITS
     objects
    4.50
     object
    4.31
    object
    3.59
     Objects
    3.58
    objects
    3.56
    Objects
    3.30
     Object
    3.23
     объекта
    3.20
     OBJECT
    3.20
    Object
    3.19
    Activations Density 0.036%

    No Known Activations