© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76874
    Prev
    Next
    INDEX
    Explanations

    Floyd Mayweather Gamma Knife

    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_34/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
     as
    -1.15
    ();
    -0.94
    딱
    -0.93
     keuangan
    -0.91
    ;
    -0.89
    ありますか
    -0.88
    ']=='
    -0.88
     just
    -0.88
     allowed
    -0.86
     again
    -0.85
    POSITIVE LOGITS
    förm
    1.13
    [:,
    1.10
     tada
    1.02
     其他
    0.98
     múl
    0.97
    ABILITY
    0.97
     innych
    0.95
     samme
    0.94
     malen
    0.94
    Likewise
    0.92
    Activations Density 0.006%

    No Known Activations