© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91405
    Prev
    Next
    INDEX
    Explanations

    news.ycombinator.com/item?id=

    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
     удовлет
    -0.72
    Happiness
    -0.72
     issuing
    -0.70
     happiness
    -0.68
     selected
    -0.67
     lifter
    -0.67
     instruction
    -0.67
     tecnico
    -0.66
    selection
    -0.66
    Symb
    -0.65
    POSITIVE LOGITS
     bindings
    0.72
    gain
    0.71
     Brin
    0.67
    estad
    0.66
    obses
    0.65
     RELATED
    0.65
    oj
    0.65
    ULDER
    0.65
    tuer
    0.64
    łyn
    0.63
    Activations Density 0.026%

    No Known Activations