© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4730
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     ت
    0.84
     Му
    0.83
     По
    0.80
     Ко
    0.76
     Pseudo
    0.75
    нено
    0.75
     الم
    0.74
     Ма
    0.73
     К
    0.73
     Mafia
    0.73
    POSITIVE LOGITS
    flexible
    0.53
    HD
    0.52
     अदर
    0.50
    삐
    0.49
    away
    0.49
    sk
    0.48
     minimise
    0.47
    sensor
    0.47
    軽量
    0.47
    hd
    0.46
    Activations Density 0.113%

    No Known Activations