© 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. 10-GEMMASCOPE-RES-131K
    7. 100626
    Prev
    Next
    INDEX
    Explanations

    commas before 'I' or 'If'

    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
     a
    -1.61
     and
    -1.53
     to
    -1.48
    …！
    -1.41
     poderão
    -1.32
     on
    -1.27
    DICTION
    -1.27
     peça
    -1.22
     úteis
    -1.20
     portuguesa
    -1.20
    POSITIVE LOGITS
    ⑴
    1.36
     nasze
    1.35
    痪
    1.34
     taką
    1.32
     они
    1.32
    Ārējās
    1.30
     there
    1.29
     examples
    1.28
     effects
    1.28
    chemia
    1.27
    Activations Density 0.014%

    No Known Activations