© 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. 34-GEMMASCOPE-RES-131K
    7. 82329
    Prev
    Next
    INDEX
    Explanations

    numbers in texts

    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_34/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
     can
    -1.24
     When
    -1.23
     Despite
    -1.12
     with
    -1.09
     M
    -1.09
    Despite
    -1.08
     make
    -1.07
     should
    -1.07
    When
    -1.07
     makes
    -1.06
    POSITIVE LOGITS
    stützung
    1.25
    真ん
    1.20
     ayur
    1.19
    IAm
    1.15
    ריס
    1.14
     vijf
    1.13
     pesso
    1.13
    Dae
    1.13
     delightful
    1.12
    kissen
    1.11
    Activations Density 0.051%

    No Known Activations