© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7285
    Prev
    Next
    INDEX
    Explanations

    asking for information or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     populace
    0.60
     어떤
    0.57
     T
    0.55
     preservation
    0.55
    hezza
    0.55
     uncharted
    0.55
    urbation
    0.53
     prowess
    0.51
     opulent
    0.51
     t
    0.50
    POSITIVE LOGITS
    Saludos
    0.86
    𝐦
    0.68
    å
    0.62
     internacionales
    0.60
    Cindy
    0.60
    ง
    0.59
    Car
    0.59
     Besar
    0.59
     argentinos
    0.59
    Colomb
    0.57
    Activations Density 1.121%

    No Known Activations