© 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. 5028
    Prev
    Next
    INDEX
    Explanations

    reach out, reach goals

    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
    ल
    2.58
    л
    2.39
    на
    2.31
     honing
    2.30
     diri
    2.06
    ations
    2.02
    د
    1.96
     پڑھیئے
    1.95
    ত্বের
    1.94
    ik
    1.93
    POSITIVE LOGITS
    ού
    2.16
    ش
    2.04
    hhhh
    1.99
    ಛ
    1.94
    ются
    1.91
     Министерство
    1.89
    ούς
    1.88
    senha
    1.86
    hh
    1.86
    зму
    1.80
    Activations Density 0.073%

    No Known Activations