© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67880
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

    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
     onsdag
    -1.98
    basically
    -1.93
    similar
    -1.84
     ideen
    -1.84
    brainly
    -1.84
     enthou
    -1.83
    simply
    -1.83
     égard
    -1.82
     menek
    -1.80
     voient
    -1.78
    POSITIVE LOGITS
     then
    2.42
     before
    2.02
     for
    1.98
     until
    1.94
     and
    1.85
     go
    1.82
     with
    1.70
     so
    1.67
     In
    1.63
     in
    1.57
    Activations Density 0.008%

    No Known Activations