© 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. 43035
    Prev
    Next
    INDEX
    Explanations

    free or cash

    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
    \&
    -2.27
     \&
    -2.25
    '
    -2.11
     '
    -1.88
    Its
    -1.86
    棪
    -1.80
    \_
    -1.75
    1
    -1.61
     $\&$
    -1.59
     gewor
    -1.59
    POSITIVE LOGITS
    en
    2.38
    ,”
    2.38
    粜
    2.28
    áculo
    2.25
    our
    2.14
    ?”
    2.11
     "..\..\..\
    2.08
    érica
    2.03
    ,’’
    2.03
     (‘
    2.00
    Activations Density 0.223%

    No Known Activations