© 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. 22-GEMMASCOPE-2-RES-262K
    7. 4195
    Prev
    Next
    INDEX
    Explanations

    in terms 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_22_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
     in
    1.55
    ใน
    1.47
     في
    1.44
     în
    1.35
    În
    1.33
     فى
    1.25
     În
    1.19
     в
    1.16
     ใน
    1.14
     در
    1.13
    POSITIVE LOGITS
     terms
    1.05
     conjunction
    0.89
     lieu
    0.89
     cafeter
    0.85
     guise
    0.82
     befind
    0.79
     accordance
    0.79
    mäß
    0.78
     torno
    0.78
    getActiveSheet
    0.73
    Activations Density 0.254%

    No Known Activations