© 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
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7377
    Prev
    Next
    INDEX
    Explanations

    calculates, calculus, academy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ありますが
    1.07
    оз
    0.98
    ас
    0.91
    商业
    0.91
    лт
    0.89
    ักษ
    0.88
     си
    0.88
    д
    0.86
    ృ
    0.86
    ប្រភេទ
    0.84
    POSITIVE LOGITS
    ̯
    1.18
    erkraut
    1.09
    casus
    1.04
    vergne
    1.02
    casian
    1.02
    Mau
    0.96
    vain
    0.95
    ßen
    0.94
    delà
    0.93
    cony
    0.93
    Activations Density 0.087%

    No Known Activations