© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8887
    Prev
    Next
    INDEX
    Explanations

    code definitions and uses

    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_13_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
     intracellular
    0.88
    💭
    0.86
    rystals
    0.85
    relativistic
    0.84
     nonlinearity
    0.84
    ithvi
    0.84
    tosecond
    0.84
     refriger
    0.84
     toxin
    0.83
    ૐ
    0.83
    POSITIVE LOGITS
     Much
    0.82
     بسیاری
    0.74
     mnogo
    0.73
     Pemerintah
    0.72
     tanti
    0.72
     Aus
    0.72
    就不
    0.71
    لن
    0.71
     much
    0.70
     pasar
    0.70
    Activations Density 0.013%

    No Known Activations