© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84188
    Prev
    Next
    INDEX
    Explanations

    saying or writing something

    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
    </h3>
    -1.92
     récompense
    -1.87
     récomp
    -1.67
     แต่
    -1.59
     déliv
    -1.59
    ⇴
    -1.48
    ifers
    -1.45
    метров
    -1.45
     форм
    -1.43
     作り方
    -1.43
    POSITIVE LOGITS
     of
    2.22
     their
    2.09
     from
    1.84
     they
    1.79
     with
    1.66
    0
    1.65
     at
    1.57
     for
    1.56
     about
    1.54
     until
    1.54
    Activations Density 0.002%

    No Known Activations