© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2143
    Prev
    Next
    INDEX
    Explanations

    play tic tac toe

    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
    タック
    1.67
     Barcl
    1.67
    mato
    1.66
     optimality
    1.65
    vorschau
    1.62
    yyum
    1.62
     impresses
    1.59
    忒
    1.59
    ramer
    1.58
     selectors
    1.58
    POSITIVE LOGITS
     Basketball
    2.45
     basketball
    2.43
    basketball
    2.41
     hobbies
    2.26
     sports
    2.25
     tennis
    2.20
    sports
    2.17
     chess
    2.16
    music
    2.15
     scuba
    2.15
    Activations Density 1.203%

    No Known Activations