© 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. 129399
    Prev
    Next
    INDEX
    Explanations

    choosing specific types or options

    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
     rése
    -1.20
     feminina
    -1.18
     fotó
    -1.13
     éto
    -1.09
    ösen
    -1.05
    𓁹
    -1.05
     pilote
    -1.04
    islands
    -1.03
    atiker
    -1.03
     perpétu
    -1.02
    POSITIVE LOGITS
     or
    1.70
     that
    1.54
     different
    1.29
     appropriate
    1.23
     available
    1.22
     suitable
    1.19
     location
    1.16
     varies
    1.16
     and
    1.13
     chosen
    1.13
    Activations Density 0.096%

    No Known Activations