© 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
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 36
    Prev
    Next
    INDEX
    Explanations

    choice and selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     Ago
    0.96
     germs
    0.92
     Cracked
    0.87
    abah
    0.87
    Incident
    0.86
     diarr
    0.86
    innis
    0.86
    詫
    0.84
     Timelapse
    0.83
    ansom
    0.83
    POSITIVE LOGITS
     choice
    3.41
     choose
    3.33
     choisir
    3.31
     choosing
    3.31
     choix
    3.30
     choices
    3.28
     escolha
    3.20
    choice
    3.19
     Choosing
    3.18
     Selection
    3.17
    Activations Density 3.623%

    No Known Activations