© 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. 92779
    Prev
    Next
    INDEX
    Explanations

    express or implied

    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
    起来
    -0.68
    typename
    -0.68
    primitives
    -0.67
     lên
    -0.67
    ogramm
    -0.66
     ridden
    -0.66
     Sincerely
    -0.66
     Lexikon
    -0.65
     equatorial
    -0.65
     serialization
    -0.65
    POSITIVE LOGITS
    خاص
    0.79
    omini
    0.76
     relentless
    0.71
     disfrute
    0.70
     گذاری
    0.69
    endan
    0.68
    см
    0.68
     affirms
    0.67
     hydrocarbons
    0.67
     stru
    0.66
    Activations Density 0.153%

    No Known Activations