© 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. 22-GEMMASCOPE-RES-131K
    7. 34873
    Prev
    Next
    INDEX
    Explanations

    end of sentence 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_22/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
     trustworthy
    -0.99
    Again
    -0.97
    new
    -0.97
     kakao
    -0.95
     rapido
    -0.93
     étrange
    -0.93
     auparavant
    -0.92
    Afterwards
    -0.92
     elefante
    -0.91
     chaussures
    -0.90
    POSITIVE LOGITS
     eventually
    1.59
     during
    1.34
     culminating
    1.33
     ultimately
    1.33
    เมื่อ
    1.31
     जब
    1.28
     uiteindelijk
    1.26
     after
    1.22
     when
    1.22
     ketika
    1.20
    Activations Density 0.071%

    No Known Activations