© 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. 8416
    Prev
    Next
    INDEX
    Explanations

    young people, youth groups

    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
     was
    -2.27
    ieuses
    -2.05
    ↵↵
    -1.98
    ிய
    -1.95
    ěji
    -1.94
     oppervlak
    -1.89
    豪华
    -1.88
    儅
    -1.82
     hemel
    -1.82
    一样的
    -1.81
    POSITIVE LOGITS
     of
    3.41
     gefördert
    2.34
    </i>
    2.17
     gespielt
    2.06
    랏
    1.99
    是很
    1.98
    Vå
    1.95
     to
    1.94
     extraordinaire
    1.93
    Ｄ
    1.93
    Activations Density 0.007%

    No Known Activations