© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9497
    Prev
    Next
    INDEX
    Explanations

    XML namespaces and attributes

    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_24_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
    지가
    0.74
    frac
    0.70
     떨어
    0.66
     }^{(
    0.65
     떨
    0.65
     όχι
    0.64
    나무
    0.64
    桃
    0.64
     ১৯৯
    0.63
    続き
    0.63
    POSITIVE LOGITS
     variabile
    0.82
     adjacency
    0.76
     accessed
    0.75
     initialized
    0.74
     eloqu
    0.73
     drawable
    0.72
     perfused
    0.71
     hemodynamic
    0.71
     adorned
    0.71
     prominently
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.