© 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. 22-GEMMASCOPE-2-RES-262K
    7. 11319
    Prev
    Next
    INDEX
    Explanations

    catch up

    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_22_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
     comprende
    1.06
    нося
    1.06
    ሶች
    1.04
    菣
    1.01
    תן
    1.00
    ológica
    0.99
    ünüz
    0.98
     descub
    0.96
    ценка
    0.96
    lés
    0.96
    POSITIVE LOGITS
     glimpse
    1.62
     glimpses
    1.53
     essence
    1.46
     essences
    1.43
     elusive
    1.43
     asympt
    1.21
     момент
    1.21
     handful
    1.20
     diathermy
    1.19
    阱
    1.17
    Activations Density 0.054%

    No Known Activations