© 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-16K
    7. 2124
    Prev
    Next
    INDEX
    Explanations

    among the

    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_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
    ه
    2.09
    ה
    2.08
    śmy
    1.90
    ్
    1.83
    я
    1.83
    де
    1.82
    as
    1.82
    o
    1.80
     birbir
    1.78
    𝙩
    1.77
    POSITIVE LOGITS
    d
    3.01
    десят
    2.54
    dde
    2.38
    েই
    2.37
    st
    2.36
    зем
    2.31
    𝚍
    2.27
    maßen
    2.21
    াধীন
    2.19
    zun
    2.05
    Activations Density 0.033%

    No Known Activations