© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4389
    Prev
    Next
    INDEX
    Explanations

    Here's why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    o
    1.68
    й
    1.65
    e
    1.49
    h
    1.42
    in
    1.40
    et
    1.36
    u
    1.32
    و
    1.30
    on
    1.28
    ه
    1.25
    POSITIVE LOGITS
    𝒂
    1.15
     פּ
    1.12
    ibility
    1.12
     Avan
    1.11
     ڈیٹا
    1.11
     Castle
    1.10
    ruitment
    1.10
     distributor
    1.10
    स्पति
    1.09
    പ്പ്
    1.07
    Activations Density 0.177%

    No Known Activations