© 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. 72542
    Prev
    Next
    INDEX
    Explanations

    and can

    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
    gleichen
    -1.51
     régal
    -1.40
    hahah
    -1.33
    fillment
    -1.31
    weiter
    -1.30
    ditionally
    -1.29
     motoru
    -1.27
    vermectin
    -1.26
     obiet
    -1.25
     signifikan
    -1.25
    POSITIVE LOGITS
     didn
    2.13
     has
    2.06
     doesn
    1.98
     isn
    1.94
     no
    1.90
     is
    1.87
     can
    1.71
     don
    1.66
     wouldn
    1.58
     have
    1.57
    Activations Density 0.034%

    No Known Activations