© 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. 4558
    Prev
    Next
    INDEX
    Explanations

    without explicit

    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
    ه
    0.73
    nicht
    0.62
     Поэтому
    0.61
     అందుకే
    0.60
    ein
    0.60
    Ein
    0.59
     Иногда
    0.58
     yüzden
    0.57
     Özellikle
    0.56
    Ç
    0.55
    POSITIVE LOGITS
     necessarily
    1.14
     resorting
    1.12
     regard
    1.07
     undue
    1.02
     recourse
    0.93
     fail
    0.88
     needing
    0.87
     hesitation
    0.84
     prejudice
    0.83
     affecting
    0.82
    Activations Density 0.031%

    No Known Activations