© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4933
    Prev
    Next
    INDEX
    Explanations

    find help

    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_22_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
     mappa
    0.81
     जाओ
    0.74
    𒀭
    0.74
     piloto
    0.74
     مها
    0.73
     admission
    0.72
     лето
    0.71
     panneau
    0.71
    comparison
    0.71
    assessment
    0.70
    POSITIVE LOGITS
    küm
    0.65
    થ
    0.64
     фактор
    0.62
    ktur
    0.58
    ñ
    0.58
     finances
    0.57
    ņas
    0.57
     onerous
    0.56
    xygen
    0.56
     অক্ষর
    0.56
    Activations Density 0.016%

    No Known Activations