© 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. 115
    Prev
    Next
    INDEX
    Explanations

    professional activities and outcomes

    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
    0.42
    2
    0.38
    4
    0.38
    3
    0.35
    8
    0.34
    9
    0.33
    6
    0.33
    7
    0.33
    HashSet
    0.32
    ითხ
    0.31
    POSITIVE LOGITS
     acumen
    0.49
     whatsoever
    0.44
     endeavors
    0.42
     empresarial
    0.41
    dreams
    0.41
     dealings
    0.40
     mishaps
    0.40
     робити
    0.39
    mates
    0.39
     lessen
    0.39
    Activations Density 0.000%

    No Known Activations