© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3440
    Prev
    Next
    INDEX
    Explanations

    #

    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
     (%
    0.66
     (?
    0.66
     ⏮
    0.65
    ()[
    0.64
     而
    0.62
     (?)
    0.62
     ("/
    0.61
     首先
    0.60
     (!
    0.59
    に
    0.59
    POSITIVE LOGITS
    instagood
    0.70
     ceramics
    0.60
     agriculture
    0.59
     copyspace
    0.59
     philippines
    0.58
     millennials
    0.57
     culturali
    0.55
     firefighters
    0.55
     policymakers
    0.55
    অপ
    0.54
    Activations Density 0.044%

    No Known Activations