© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11284
    Prev
    Next
    INDEX
    Explanations

    German words, Turkish words, Russian words

    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_9_width_262k_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
     aikana
    1.49
    en
    1.43
    ть
    1.36
    id
    1.33
    admins
    1.32
    s
    1.31
    țile
    1.29
    sı
    1.22
     बारे
    1.21
    ske
    1.21
    POSITIVE LOGITS
    дні
    1.57
    ์
    1.43
    ść
    1.30
    ज़ाइन
    1.28
    కి
    1.27
    ই
    1.24
    д
    1.24
    ك
    1.21
    ﺔ
    1.17
    𝗛
    1.15
    Activations Density 0.012%

    No Known Activations