© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12370
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
    (=
    0.70
     )
    0.64
     trivially
    0.63
    N
    0.63
     ("
    0.62
    ()
    0.62
    POSIX
    0.62
    V
    0.62
    F
    0.61
     (=
    0.59
    POSITIVE LOGITS
     pięk
    0.93
     perjalanan
    0.93
     alegria
    0.89
     alegría
    0.88
     calme
    0.84
     incroyable
    0.84
     jährlich
    0.83
     całkow
    0.83
     prachtige
    0.82
     heartfelt
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.