© 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. 22252
    Prev
    Next
    INDEX
    Explanations

    morphological and linguistic domains

    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
    al
    -1.70
    an
    -1.69
    ou
    -1.58
    or
    -1.56
    "...
    -1.55
    f
    -1.53
    our
    -1.48
    "-
    -1.47
    un
    -1.45
    ano
    -1.45
    POSITIVE LOGITS
     originalmente
    1.43
     全国
    1.42
     olika
    1.42
     浴
    1.41
     MANY
    1.41
    vielen
    1.40
    mudah
    1.38
    формы
    1.38
    julie
    1.35
     figlio
    1.34
    Activations Density 0.023%

    No Known Activations