© 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. 10-GEMMASCOPE-RES-131K
    7. 12271
    Prev
    Next
    INDEX
    Explanations

    entry or entrance

    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_10/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
    u
    -2.91
    ’
    -2.78
    ta
    -2.55
    “
    -2.55
    z
    -2.55
    r
    -2.48
    X
    -2.36
    0
    -2.34
    k
    -2.33
    m
    -2.31
    POSITIVE LOGITS
     into
    2.80
    StoryboardSegue
    2.78
    
    2.73
    derdag
    2.53
    Donativos
    2.38
    荜
    2.25
    brinco
    2.19
    lysm
    2.16
     Each
    2.13
    ureusement
    2.11
    Activations Density 0.006%

    No Known Activations