© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9288
    Prev
    Next
    INDEX
    Explanations

    Baltimore, Hamburg, MATLAB contexts

    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
     вот
    2.35
     viso
    2.22
    Į
    2.19
     piggy
    2.18
    ことで
    2.14
     eben
    2.14
    لون
    2.11
     eradic
    2.11
     JAS
    2.10
     ομά
    2.09
    POSITIVE LOGITS
    ار
    3.32
    ی
    2.70
    м
    2.67
    ла
    2.61
    ిన
    2.59
    к
    2.56
     dwind
    2.37
    te
    2.36
    짭
    2.30
    buscador
    2.27
    Activations Density 0.001%

    No Known Activations