© 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. 39597
    Prev
    Next
    INDEX
    Explanations

    many, numerous, several, various, countless

    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
     it
    -1.44
     its
    -1.31
    它
    -1.25
    ;|
    -1.23
    它是
    -1.23
    ()
    -1.22
    -1.20
     estamos
    -1.20
    };
    -1.18
     seperti
    -1.18
    POSITIVE LOGITS
    Até
    1.46
    Também
    1.37
    Onde
    1.36
    衚
    1.34
    Beruf
    1.34
    Εκ
    1.30
    CAPÍTULO
    1.28
    引言
    1.27
     of
    1.26
    Ancien
    1.26
    Activations Density 0.012%

    No Known Activations