© 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. 1231
    Prev
    Next
    INDEX
    Explanations

    from your

    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
    zare
    1.73
    aprendizaje
    1.64
    ំហ
    1.62
    ب
    1.57
    werking
    1.54
    לע
    1.52
     fique
    1.48
    larda
    1.45
    𝐖
    1.44
    ো
    1.44
    POSITIVE LOGITS
    the
    1.62
    0
    1.36
    1
    1.36
     linger
    1.26
    2
    1.25
    4
    1.25
    𖥔
    1.25
     truncated
    1.24
    <bos>
    1.23
     ما
    1.20
    Activations Density 0.846%

    No Known Activations