© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84520
    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_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
     as
    -3.25
     or
    -3.20
     especially
    -2.61
     et
    -2.45
     also
    -2.44
     even
    -2.39
     they
    -2.38
     time
    -2.36
     and
    -2.25
     because
    -2.25
    POSITIVE LOGITS
    ⡃
    2.48
    .
    2.45
     faciliter
    2.39
     diriger
    2.38
     camiset
    2.30
    糁
    2.28
    镡
    2.27
     Hanya
    2.22
     garantir
    2.19
    -“
    2.17
    Activations Density 0.011%

    No Known Activations