© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 13990
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    いち
    1.73
     sogen
    1.49
     deterioro
    1.48
    𝙙
    1.47
     resultado
    1.47
    𝙞
    1.46
     enige
    1.45
     localização
    1.43
     desactiv
    1.41
    𝙡
    1.41
    POSITIVE LOGITS
    ierungen
    1.92
    ر
    1.78
    р
    1.71
    us
    1.66
    ع
    1.58
    లు
    1.52
    j
    1.51
    ными
    1.40
    веден
    1.39
    வு
    1.39
    Activations Density 0.000%

    No Known Activations