© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14002
    Prev
    Next
    INDEX
    Explanations

    scientific concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     personable
    0.79
     Pursuant
    0.77
     muß
    0.73
    ल्फ़
    0.69
     totaling
    0.68
    referenced
    0.66
     envisioned
    0.66
    ̡
    0.65
    ɰ
    0.65
     equaling
    0.64
    POSITIVE LOGITS
     coloured
    0.95
     colour
    0.91
     upto
    0.85
    ਸ਼
    0.83
     radiations
    0.81
     flavoured
    0.80
     tyres
    0.80
     inbuilt
    0.77
     irrespective
    0.77
     wastage
    0.77
    Activations Density 0.015%

    No Known Activations