© 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. 22-GEMMASCOPE-2-RES-262K
    7. 943
    Prev
    Next
    INDEX
    Explanations

    in a phrase

    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
     внутрен
    1.55
    在
    1.53
    ك
    1.43
    கள்
    1.35
    În
    1.35
    د
    1.28
    क
    1.25
    de
    1.19
    taking
    1.17
    tis
    1.15
    POSITIVE LOGITS
     handy
    1.46
     accordance
    1.44
     vitro
    1.41
     vivo
    1.38
    verters
    1.32
     terms
    1.29
     conjunction
    1.28
     spite
    1.23
    ordinate
    1.21
     качестве
    1.19
    Activations Density 0.081%

    No Known Activations