© 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. 34-GEMMASCOPE-RES-131K
    7. 3105
    Prev
    Next
    INDEX
    Explanations

    preposition followed by acronym or specific noun

    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
     imágen
    -1.28
    骉
    -1.24
     nieuwe
    -1.20
     wielu
    -1.20
     tych
    -1.19
     kostenlose
    -1.19
     '"
    -1.15
    !!!!!!
    -1.14
    vonne
    -1.13
     cómoda
    -1.13
    POSITIVE LOGITS
     or
    1.31
     yPos
    1.28
     both
    1.27
     although
    1.24
     when
    1.22
     Initially
    1.20
     during
    1.20
     When
    1.17
     homogenous
    1.16
     Hardcover
    1.14
    Activations Density 0.311%

    No Known Activations