© 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. 71312
    Prev
    Next
    INDEX
    Explanations

    sort of

    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
    蚡
    -2.39
    葎
    -2.38
    垸
    -2.34
    ᯾
    -2.30
    ſche
    -2.30
     própri
    -2.30
     parachoque
    -2.28
    鸶
    -2.25
    ESSIONAL
    -2.20
    
    -2.20
    POSITIVE LOGITS
    </h3>
    4.06
    '
    3.94
    “
    3.33
     ‘
    2.84
    ”
    2.83
    .”
    2.81
    </i>
    2.81
     ’
    2.80
    a
    2.75
    "
    2.73
    Activations Density 0.004%

    No Known Activations