© 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. 210709
    Prev
    Next
    INDEX
    Explanations

    hand of

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

    AI or child content

    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
     மனம்
    0.51
     ক্রোধ
    0.48
     dukkh
    0.46
     ឬ
    0.45
    }]$
    0.45
     všechny
    0.43
    पत्नी
    0.43
    कार्बन
    0.43
    ᱽ
    0.43
     الخمسه
    0.43
    POSITIVE LOGITS
     de
    0.60
     in
    0.52
     ZH
    0.47
     HIG
    0.46
     comest
    0.44
    在
    0.44
    hig
    0.43
    Kom
    0.43
    पूर्ति
    0.43
    mpi
    0.42
    Activations Density 0.000%

    No Known Activations