© 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. 23946
    Prev
    Next
    INDEX
    Explanations

    lists of options or results

    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
    During
    -1.36
     also
    -1.36
     cage
    -1.33
     characteristics
    -1.30
     During
    -1.29
     could
    -1.27
     of
    -1.27
    aní
    -1.26
     might
    -1.24
     but
    -1.23
    POSITIVE LOGITS
     nying
    1.30
    varande
    1.25
    comers
    1.18
    versus
    1.14
     fz
    1.13
    c
    1.12
    or
    1.12
     utveckling
    1.11
     dito
    1.09
    給你
    1.08
    Activations Density 0.149%

    No Known Activations