© 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. 108313
    Prev
    Next
    INDEX
    Explanations

    now that

    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
    gave
    -1.05
    totta
    -1.05
     nunca
    -1.04
     actuellement
    -1.02
    created
    -1.02
    苤
    -1.01
    今でも
    -1.01
    Библи
    -0.99
     nowadays
    -0.98
    
    -0.98
    POSITIVE LOGITS
     that
    3.11
     it
    2.06
    Here
    1.50
     with
    1.50
    days
    1.42
     they
    1.40
     we
    1.39
     there
    1.31
     comes
    1.30
     setelah
    1.29
    Activations Density 0.023%

    No Known Activations