© 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. 101886
    Prev
    Next
    INDEX
    Explanations

    reporting and quoting speech

    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
    ⟞
    -1.80
    铙
    -1.47
    𓐍
    -1.46
     renou
    -1.42
    discussed
    -1.40
    狴
    -1.40
     yeter
    -1.39
    𓍊
    -1.38
    お試し
    -1.38
    uating
    -1.37
    POSITIVE LOGITS
     or
    1.48
     said
    1.33
     various
    1.27
    בה
    1.24
    }$,
    1.20
     many
    1.19
    zelfde
    1.19
     but
    1.16
     both
    1.15
     several
    1.15
    Activations Density 0.048%

    No Known Activations