© 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. 10-GEMMASCOPE-RES-131K
    7. 67159
    Prev
    Next
    INDEX
    Explanations

    on [noun/phrase]

    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
    </b>
    -1.42
    horas
    -1.14
     "
    -1.11
    なんですが
    -1.08
     all
    -1.01
    ẋ
    -0.98
     Also
    -0.98
     at
    -0.97
     vuestro
    -0.97
     geniş
    -0.96
    POSITIVE LOGITS
    formatics
    1.55
     of
    1.44
    sistence
    1.36
    formazioni
    1.33
    vertebrates
    1.30
    vaders
    1.27
    ⟞
    1.27
     pagina
    1.27
    secta
    1.26
    cursions
    1.25
    Activations Density 0.160%

    No Known Activations