© 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. 8402
    Prev
    Next
    INDEX
    Explanations

    clear function definition

    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
    ৪
    2.02
    ्स
    1.97
     Volumes
    1.95
    ння
    1.89
     Expressions
    1.88
    ८
    1.86
     Reserves
    1.84
    day
    1.81
     Вер
    1.81
     Intervals
    1.80
    POSITIVE LOGITS
    ر
    2.14
    아야
    2.09
    AL
    2.08
    ALITY
    2.08
    DONT
    1.98
    un
    1.98
     juríd
    1.98
    っぷ
    1.98
    ﯽ
    1.95
    Clique
    1.94
    Activations Density 0.348%

    No Known Activations