© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14582
    Prev
    Next
    INDEX
    Explanations

    step-by-step explanations

    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
    Consequently
    1.01
     ultimately
    0.95
     Consequently
    0.93
    Ultimately
    0.86
     (&
    0.85
     sämt
    0.84
    Describes
    0.84
    Alongside
    0.83
    isely
    0.83
    Accordingly
    0.83
    POSITIVE LOGITS
     роман
    1.00
     sarcastic
    0.88
     cashier
    0.87
    ر
    0.85
     mother
    0.83
     сайт
    0.82
    tif
    0.79
     doubtful
    0.79
     Shia
    0.79
     confuses
    0.78
    Activations Density 0.151%

    No Known Activations