© 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. 131897
    Prev
    Next
    INDEX
    Explanations

    dumpster capacity and handling

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

    listening to identify key points

    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
     characters
    0.46
     genotypes
    0.46
     strands
    0.46
    <0x0D>
    0.44
     tissues
    0.44
     kilograms
    0.44
     sutures
    0.44
    壽
    0.44
     unsatisfactory
    0.44
     haunts
    0.43
    POSITIVE LOGITS
    law
    0.49
    itm
    0.49
    tabPadding
    0.49
    یکه
    0.49
     ब्रिटेन
    0.46
     понял
    0.46
     وە
    0.46
     позволит
    0.46
    itamos
    0.46
     विस्त
    0.45
    Activations Density 0.002%

    No Known Activations