© 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. 66933
    Prev
    Next
    INDEX
    Explanations

    quantas vezes, when, Quanti

    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
    櫺
    -2.44
    孓
    -2.28
     This
    -2.28
     consentimiento
    -2.28
    upuncture
    -2.17
    ’，
    -2.14
    頔
    -2.13
    我不
    -2.09
     increasingly
    -2.09
    ühnen
    -2.06
    POSITIVE LOGITS
     \
    2.89
    ↵↵
    2.70
    <em>
    2.66
     —
    2.34
    桫
    2.22
    </strong>
    2.20
    </em>
    2.20
                    
    2.20
               
    2.17
    了很多
    2.17
    Activations Density 0.001%

    No Known Activations