© 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. 111667
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
    '
    -3.36
    -
    -2.36
     enmar
    -2.28
    僦
    -2.28
    ?
    -2.25
    ’
    -2.25
            
    -2.19
    }\
    -2.16
     hará
    -2.13
     noved
    -2.13
    POSITIVE LOGITS
    or
    2.56
    Ꮌ
    2.30
    givers
    2.30
     dici
    2.23
    when
    2.23
    摃
    2.23
    comings
    2.22
    ized
    2.20
     nava
    2.17
    ſelf
    2.16
    Activations Density 0.012%

    No Known Activations