© 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. 49136
    Prev
    Next
    INDEX
    Explanations

    man in the world

    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
    のですか
    -1.09
     сейчас
    -0.90
     dziś
    -0.86
     propriedade
    -0.84
     ORIGINAL
    -0.83
     trov
    -0.82
     فع
    -0.82
     gefunden
    -0.82
    וֹ
    -0.81
    chtigkeit
    -0.80
    POSITIVE LOGITS
     imaginable
    2.47
     in
    1.78
     there
    1.75
     ever
    1.59
     on
    1.59
     known
    1.57
     conceivable
    1.43
     anyone
    1.41
     alive
    1.37
    imagin
    1.30
    Activations Density 0.030%

    No Known Activations