© 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. 128209
    Prev
    Next
    INDEX
    Explanations

    Bung, cef, armature, Aure

    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
    然后
    -2.80
    </b>
    -2.78
     nacido
    -2.64
    知らない
    -2.61
     —
    -2.58
    l
    -2.47
    t
    -2.45
     pensar
    -2.42
     If
    -2.23
    ...
    -2.22
    POSITIVE LOGITS
    ၞ
    3.30
    鳊
    3.20
    澐
    3.16
    cuerdo
    3.05
     scrutin
    3.02
    ୌ
    2.97
    鈊
    2.72
    蕺
    2.69
    ༵
    2.66
     sprüche
    2.64
    Activations Density 0.017%

    No Known Activations