© 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. 112550
    Prev
    Next
    INDEX
    Explanations

    I guess / we guess

    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
    焄
    -1.68
    蠵
    -1.62
     joyería
    -1.61
    ࿚
    -1.60
    \}$,
    -1.60
    дных
    -1.59
     prezenta
    -1.59
    鼷
    -1.59
    </b>
    -1.59
    sukienka
    -1.58
    POSITIVE LOGITS
    各样的
    1.66
     they
    1.50
    他に
    1.48
     ‘
    1.47
    </h3>
    1.42
    ’;
    1.41
     Ensuring
    1.39
     erheblich
    1.39
     ’
    1.38
    の中で
    1.38
    Activations Density 0.004%

    No Known Activations