© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101529
    Prev
    Next
    INDEX
    Explanations

    set foot

    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
     partout
    -1.36
    ESTE
    -1.29
    rste
    -1.29
     alguém
    -1.27
    »
    -1.25
    ",
    -1.20
    en
    -1.20
    </table>
    -1.18
     временем
    -1.18
    ">
    -1.16
    POSITIVE LOGITS
     until
    1.66
     except
    1.37
     during
    1.35
     these
    1.30
     while
    1.27
     gespannt
    1.25
     instead
    1.23
    ᐕ
    1.22
     or
    1.21
     much
    1.20
    Activations Density 0.051%

    No Known Activations