© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3234
    Prev
    Next
    INDEX
    Explanations

    project discreetly

    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_7_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
    кина
    1.97
    日至
    1.74
    ඟ
    1.73
    Subview
    1.72
     числе
    1.71
    టే
    1.71
    തും
    1.66
    ಬು
    1.62
    هن
    1.61
    冨
    1.59
    POSITIVE LOGITS
    rakk
    1.48
    갬
    1.41
     Mise
    1.41
    loser
    1.39
     aven
    1.37
     aes
    1.36
    براین
    1.34
     egg
    1.33
     erode
    1.32
    URANCE
    1.32
    Activations Density 0.000%

    No Known Activations