© 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. 63121
    Prev
    Next
    INDEX
    Explanations

    specific qualities or states

    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
    :
    -1.36
    着一个
    -1.32
     diversos
    -1.30
     alcune
    -1.30
    了很多
    -1.27
     alcuni
    -1.24
    了几
    -1.22
     frites
    -1.20
     scénario
    -1.18
     a
    -1.16
    POSITIVE LOGITS
     cocinas
    1.59
     بگیرید
    1.56
     and
    1.49
     versions
    1.48
     but
    1.46
     antiguas
    1.44
     Envío
    1.41
     combinations
    1.39
     creativos
    1.39
     methods
    1.35
    Activations Density 0.593%

    No Known Activations