© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93707
    Prev
    Next
    INDEX
    Explanations

    turns out to be proven

    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
     octa
    -0.80
     Piz
    -0.79
    YES
    -0.79
    nante
    -0.78
    pdb
    -0.77
    hyrchwyd
    -0.77
     gillar
    -0.75
    hver
    -0.74
    словно
    -0.73
    〘
    -0.73
    POSITIVE LOGITS
     prove
    6.22
     proving
    5.69
     proves
    5.69
     proved
    5.41
    prove
    4.84
     Prove
    4.41
    Prove
    4.28
    proved
    4.25
     Proving
    3.89
     proven
    3.75
    Activations Density 0.216%

    No Known Activations