© 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. 4467
    Prev
    Next
    INDEX
    Explanations

    is where

    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
     различных
    0.98
    ಿಸಬಹುದು
    0.94
    的一些
    0.92
     különböző
    0.91
     любых
    0.89
     животных
    0.86
    私は
    0.85
    ቖ
    0.84
     средств
    0.83
     другие
    0.82
    POSITIVE LOGITS
     what
    2.89
     where
    2.79
    what
    2.42
    where
    2.40
     how
    2.17
     why
    2.07
     Where
    2.07
    Where
    2.06
     donde
    1.94
     whats
    1.93
    Activations Density 0.379%

    No Known Activations