© 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. 702
    Prev
    Next
    INDEX
    Explanations

    markdown formatting and code delimiters

    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
     sbParams
    0.71
     ৮
    0.65
     sofern
    0.64
     zwölf
    0.64
    𝟯
    0.63
     ۳
    0.62
    Toast
    0.61
    Lemon
    0.61
    හෝ
    0.60
    UIAlert
    0.60
    POSITIVE LOGITS
    ir
    0.73
    ik
    0.66
    yn
    0.58
    ina
    0.57
    ak
    0.55
    ed
    0.55
    em
    0.55
    ag
    0.54
    il
    0.53
    k
    0.52
    Activations Density 0.240%

    No Known Activations