© 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. 129063
    Prev
    Next
    INDEX
    Explanations

    European languages

    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
     ناد
    -1.03
     亜
    -0.95
    然后
    -0.82
     unfavorable
    -0.82
    </tbody>
    -0.81
    quakes
    -0.80
    ródła
    -0.80
    !--
    -0.79
    formazioni
    -0.79
    !
    -0.78
    POSITIVE LOGITS
     into
    0.88
     tölt
    0.84
     espagnole
    0.79
     zü
    0.78
     italienne
    0.73
    }};
    0.73
    渔
    0.73
    preuves
    0.72
    itoare
    0.72
     prêtres
    0.72
    Activations Density 0.043%

    No Known Activations