© 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. 22-GEMMASCOPE-RES-131K
    7. 129001
    Prev
    Next
    INDEX
    Explanations

    dialog content

    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_22/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
     if
    -1.11
     from
    -1.09
     on
    -1.08
     as
    -1.06
     to
    -1.04
     since
    -0.94
     each
    -0.94
     by
    -0.85
     should
    -0.84
     eorum
    -0.82
    POSITIVE LOGITS
     umożli
    1.00
    čius
    0.99
    remos
    0.97
     surprise
    0.97
    signee
    0.96
    کارت
    0.96
    arynx
    0.95
    estanding
    0.94
     vincere
    0.94
    Exelente
    0.92
    Activations Density 0.013%

    No Known Activations