© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71354
    Prev
    Next
    INDEX
    Explanations

    word followed by specific noun or preposition

    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_10/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
     either
    -1.33
     also
    -1.20
     already
    -1.19
    ceedings
    -1.10
     dicha
    -1.09
     amortecedor
    -1.05
     también
    -1.05
     include
    -1.03
     også
    -1.02
     cantora
    -1.02
    POSITIVE LOGITS
    imdi
    1.09
    0
    1.06
     mereka
    1.04
     _('
    1.04
    螂
    1.02
    Prze
    0.99
    they
    0.99
    дото
    0.98
     dwar
    0.96
     bersama
    0.93
    Activations Density 0.094%

    No Known Activations