© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111625
    Prev
    Next
    INDEX
    Explanations

    self and own

    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
     is
    -1.88
     it
    -1.88
     "
    -1.86
     you
    -1.83
    </b>
    -1.80
     Which
    -1.70
     he
    -1.69
     Our
    -1.65
     Other
    -1.61
     can
    -1.58
    POSITIVE LOGITS
    鹩
    2.05
    铪
    1.99
    Татьяна
    1.86
     ſie
    1.81
    ญี่ป
    1.80
    ☫
    1.78
    錞
    1.78
    ︕
    1.76
    炱
    1.74
    ⸂
    1.70
    Activations Density 0.004%

    No Known Activations