© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12509
    Prev
    Next
    INDEX
    Explanations

    Explain or discuss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Which
    0.89
    Which
    0.87
    哪个
    0.75
     When
    0.73
     A
    0.72
     Each
    0.71
    Question
    0.71
    A
    0.71
     If
    0.71
    Questions
    0.71
    POSITIVE LOGITS
     explain
    1.44
     expliquer
    1.25
     explique
    1.23
     explicar
    1.20
    explain
    1.18
     explicando
    1.17
     explained
    1.14
     explica
    1.14
     explaining
    1.13
     объяс
    1.12
    Activations Density 0.024%

    No Known Activations