© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7424
    Prev
    Next
    INDEX
    Explanations

    infinitely far

    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
     ficou
    0.59
    étique
    0.58
    陷
    0.58
    ंजय
    0.56
    वाह
    0.55
    ãos
    0.55
    Kann
    0.55
    乍
    0.54
    ivant
    0.54
    wek
    0.54
    POSITIVE LOGITS
     Sleeps
    0.52
     Kelly
    0.52
     grizzly
    0.50
    これは
    0.49
     Salt
    0.49
    Kelly
    0.48
     SEEK
    0.48
    森
    0.48
     गोष्टी
    0.48
     činjen
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.