© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151430
    Prev
    Next
    INDEX
    Explanations

    investigation of, degrees will, by sending

    np_acts-logits-general · gemini-2.5-flash-lite

    ```.\nsystemexample```

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     t
    0.59
     week
    0.48
     th
    0.48
     votre
    0.47
     eller
    0.47
     your
    0.46
    <0xA9>
    0.46
     tych
    0.46
     Hurd
    0.45
     >
    0.45
    POSITIVE LOGITS
    Objet
    0.48
    Encom
    0.48
    птова
    0.47
    מח
    0.46
    客户端
    0.45
    罨
    0.44
    Ét
    0.44
     топли
    0.43
    بھ
    0.42
    Clients
    0.42
    Activations Density 0.000%

    No Known Activations