© 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. 116707
    Prev
    Next
    INDEX
    Explanations

    Python for loops

    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
     verschillende
    -1.48
    Вариан
    -1.30
    apparently
    -1.30
    Fourni
    -1.30
    Gruss
    -1.30
    various
    -1.29
    Бил
    -1.27
    Mvh
    -1.26
     persoonlijke
    -1.24
    Цита
    -1.23
    POSITIVE LOGITS
     i
    2.22
     in
    2.02
     _,
    1.86
     (
    1.85
     each
    1.84
     I
    1.75
    _);
    1.37
     Each
    1.30
    }\
    1.30
    }$,
    1.30
    Activations Density 0.007%

    No Known Activations