© 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. 40110
    Prev
    Next
    INDEX
    Explanations

    dolphins and Sensors

    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
     ſont
    -2.63
    𝐬
    -2.38
     pueda
    -2.34
    of
    -2.31
     finnas
    -2.27
     交換
    -2.23
     curtail
    -2.23
     mehreren
    -2.22
    !'
    -2.20
     aktuellen
    -2.20
    POSITIVE LOGITS
    </td>
    3.42
        
    2.97
    <bos>
    2.81
    O
    2.80
     για
    2.67
    ↵↵
    2.47
     untuk
    2.39
     utilizing
    2.36
     heo
    2.31
     ſta
    2.28
    Activations Density 0.004%

    No Known Activations