© 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. 12-GEMMASCOPE-2-RES-16K
    7. 427
    Prev
    Next
    INDEX
    Explanations

    punctuated questions

    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_12_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
    9
    0.63
    7
    0.62
    6
    0.59
    8
    0.59
    4
    0.55
    3
    0.53
    5
    0.52
    ৬
    0.52
     maroon
    0.50
    ٩
    0.50
    POSITIVE LOGITS
     that
    0.54
     and
    0.53
     thinkers
    0.49
     situations
    0.48
     extremes
    0.46
     if
    0.45
    לות
    0.45
     doesn
    0.44
     없다
    0.43
     Laws
    0.42
    Activations Density 0.633%

    No Known Activations