© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 45280
    Prev
    Next
    INDEX
    Explanations

    line, beam, fire, flow

    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
    ter
    0.71
     novice
    0.69
    ِّ
    0.69
    IN
    0.68
    teros
    0.67
     برج
    0.66
    BackgroundHelper
    0.66
    )):
    0.64
     trek
    0.64
    気分
    0.63
    POSITIVE LOGITS
     який
    0.93
     Trouvez
    0.91
     который
    0.79
     Ultrasound
    0.77
    isuus
    0.77
     вважа
    0.76
    یاں
    0.75
    erView
    0.75
    ர்வு
    0.75
     Това
    0.74
    Activations Density 0.000%

    No Known Activations