© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116990
    Prev
    Next
    INDEX
    Explanations

    phrases with 'out'

    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
    Off
    -1.38
    Down
    -1.14
    Up
    -1.11
     Off
    -1.05
    off
    -0.99
    Away
    -0.95
    OFF
    -0.86
    down
    -0.84
    Into
    -0.82
    DOWN
    -0.81
    POSITIVE LOGITS
     out
    1.95
    rape
    0.87
    uhe
    0.73
    -------
    0.73
    anni
    0.71
    漕
    0.71
    置く
    0.71
     night
    0.71
    quelle
    0.70
    Dau
    0.69
    Activations Density 0.068%

    No Known Activations