© 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. 34-GEMMASCOPE-RES-131K
    7. 117706
    Prev
    Next
    INDEX
    Explanations

    calling parent methods

    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
     disfrutando
    -0.89
     obtend
    -0.88
     매우
    -0.88
     extinción
    -0.87
    我们就
    -0.86
     emprender
    -0.85
     事業
    -0.84
     δύο
    -0.84
    EDING
    -0.83
     respald
    -0.83
    POSITIVE LOGITS
     herman
    0.95
    );
    0.90
     mitad
    0.89
     ////
    0.89
    ธอ
    0.84
    の場合
    0.84
    ：“……”
    0.83
     also
    0.83
    穹
    0.81
     geographical
    0.80
    Activations Density 0.002%

    No Known Activations