© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48248
    Prev
    Next
    INDEX
    Explanations

    file system paths

    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
    Follow
    -0.85
    @$
    -0.77
     bezpośred
    -0.74
    将于
    -0.74
    Meanwhile
    -0.74
    oose
    -0.74
    textInput
    -0.71
    Fall
    -0.71
    ynth
    -0.70
     Konsequ
    -0.70
    POSITIVE LOGITS
     normalize
    0.84
     Paths
    0.82
    normalize
    0.77
     郭
    0.77
     Patriots
    0.77
    🏚
    0.75
     pathlib
    0.75
    ælp
    0.74
    normalization
    0.74
     GREY
    0.73
    Activations Density 0.003%

    No Known Activations