© 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. 59673
    Prev
    Next
    INDEX
    Explanations

    introduction or details

    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
    のに
    -0.73
    OUBLE
    -0.71
    inking
    -0.71
    餡
    -0.68
    TBA
    -0.68
    CIP
    -0.63
    isma
    -0.62
    トイ
    -0.62
     keine
    -0.62
    DCHECK
    -0.62
    POSITIVE LOGITS
    ={()
    0.79
     curiosity
    0.77
    рим
    0.73
    痛
    0.71
    Acceptance
    0.71
    mado
    0.71
     لیتر
    0.71
     READ
    0.69
    Boiling
    0.69
     invariance
    0.69
    Activations Density 0.011%

    No Known Activations