© 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. 108856
    Prev
    Next
    INDEX
    Explanations

    code continuation; specific terms

    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
     Carmine
    -0.73
     direction
    -0.68
    amesh
    -0.66
    JMenuBar
    -0.66
     ordem
    -0.66
    Malloc
    -0.66
    climb
    -0.65
     جلد
    -0.65
     piping
    -0.64
     bleibt
    -0.63
    POSITIVE LOGITS
    áló
    0.69
     recto
    0.69
     core
    0.66
    INFINITY
    0.65
    كتاب
    0.65
    deld
    0.64
     Tagore
    0.63
     beraten
    0.62
    скільки
    0.62
     Bajos
    0.61
    Activations Density 0.057%

    No Known Activations