© 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. 34-GEMMASCOPE-RES-131K
    7. 93087
    Prev
    Next
    INDEX
    Explanations

    Still looking for

    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
     in
    -1.45
     of
    -1.44
     from
    -1.38
     like
    -1.16
     within
    -1.14
     because
    -1.13
     on
    -1.09
     at
    -1.06
     which
    -1.06
     started
    -1.05
    POSITIVE LOGITS
    maximize
    1.03
     note
    0.98
    ;
    0.96
     Ольга
    0.96
     gebunden
    0.95
     foncé
    0.95
    ꦼ
    0.95
     rey
    0.95
    ceni
    0.95
    lllll
    0.94
    Activations Density 0.006%

    No Known Activations