© 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. 129031
    Prev
    Next
    INDEX
    Explanations

    companion

    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
    𓐍
    -2.59
     posteriormente
    -2.34
     grosse
    -2.30
    鷂
    -2.22
    unuz
    -2.22
     encontramos
    -2.14
     jejich
    -2.13
    鹪
    -2.13
     большая
    -2.11
     takže
    -2.11
    POSITIVE LOGITS
    n
    2.58
    荐
    2.34
    极了
    2.23
    というわけで
    2.20
    </td>
    2.19
     σε
    2.13
    特别是
    2.11
     But
    2.11
     में
    2.09
    代わりに
    2.08
    Activations Density 0.007%

    No Known Activations