© 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. 2236
    Prev
    Next
    INDEX
    Explanations

    risk of

    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
    ul
    1.91
    깐
    1.83
     kaun
    1.70
    ുന്ന
    1.69
    क
    1.68
    za
    1.67
     fils
    1.65
    ்கு
    1.59
    ົວ
    1.57
    вет
    1.56
    POSITIVE LOGITS
    y
    2.48
     orthogonality
    2.02
    dtd
    1.92
    iance
    1.87
    یه
    1.86
    a
    1.85
    هِ
    1.84
    recv
    1.82
     handelt
    1.82
    Challenges
    1.81
    Activations Density 0.215%

    No Known Activations