© 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. 101570
    Prev
    Next
    INDEX
    Explanations

    guest rooms, apartments, appearances, roles

    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
    麃
    -2.03
    鋨
    -2.02
    )»
    -1.97
    魮
    -1.94
    »:
    -1.82
    豋
    -1.80
    
    -1.80
    韪
    -1.74
    établir
    -1.74
    ?");
    -1.74
    POSITIVE LOGITS
    ’
    1.80
     from
    1.78
    に関して
    1.73
    "
    1.70
     us
    1.63
     array
    1.62
    ,
    1.61
     llena
    1.61
     of
    1.59
     idealistic
    1.58
    Activations Density 0.009%

    No Known Activations