© 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-262K
    7. 11961
    Prev
    Next
    INDEX
    Explanations

    and explaining reasons

    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_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
    cet
    1.13
     wrist
    1.12
     versatile
    1.10
    rí
    1.10
     przyn
    1.09
    щены
    1.08
    য়াম
    1.06
     ì
    1.04
    ला
    1.02
     hội
    1.02
    POSITIVE LOGITS
    すなわち
    1.57
     Wouldn
    1.52
     fossero
    1.49
     dotycz
    1.47
     wäre
    1.40
     दूसरे
    1.37
     bahwa
    1.36
    于是
    1.33
     dotyczące
    1.32
     bahawa
    1.31
    Activations Density 0.087%

    No Known Activations