© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15694
    Prev
    Next
    INDEX
    Explanations

    numbers and specific details

    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
    ually
    0.23
    ieren
    0.21
     serien
    0.21
    /
    0.20
    ing
    0.20
    lett
    0.20
    ont
    0.20
    itha
    0.20
    <s>
    0.19
    ward
    0.19
    POSITIVE LOGITS
     immersed
    0.20
    葢
    0.20
     coarsely
    0.19
    tbLabel
    0.19
    тың
    0.19
     steeped
    0.18
     elastomer
    0.18
     groomed
    0.18
     appealing
    0.18
     Zh
    0.18
    Activations Density 0.000%

    No Known Activations