© 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. 14083
    Prev
    Next
    INDEX
    Explanations

    it is no surprise that

    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
    </strong>
    -1.62
    }$
    -1.60
    R
    -1.48
    Masukkan
    -1.47
    </sup>
    -1.47
     what
    -1.46
    </sub>
    -1.45
    いわゆる
    -1.44
     /*
    -1.43
    although
    -1.41
    POSITIVE LOGITS
    ísa
    1.53
    諉
    1.53
     retourne
    1.52
     conseille
    1.50
     prépare
    1.40
     exé
    1.38
    vraag
    1.38
     consiguiente
    1.36
     fattori
    1.36
     confirmación
    1.35
    Activations Density 0.015%

    No Known Activations