© 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. 915
    Prev
    Next
    INDEX
    Explanations

    application, input, really

    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
    er
    1.36
    й
    1.29
    ी
    1.18
     dossier
    1.13
    ре
    1.13
    ीकरण
    1.11
     dépenses
    1.10
    uter
    1.10
     egli
    1.10
     atracción
    1.07
    POSITIVE LOGITS
    ர்க
    1.15
    ات
    1.04
    ⑅
    0.98
    owners
    0.98
     Ç
    0.96
     Bark
    0.96
    洖
    0.95
    ্থ
    0.95
    porque
    0.94
     Ñ
    0.94
    Activations Density 0.000%

    No Known Activations