© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6573
    Prev
    Next
    INDEX
    Explanations

    software reader fenómeno gas started returning

    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_65k_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
    ?\
    1.05
    م
    1.05
     sute
    1.04
     [\
    1.04
    |\
    1.02
     '\
    1.01
     трех
    0.98
     \<
    0.97
    ...\
    0.97
     CIP
    0.97
    POSITIVE LOGITS
    гласно
    1.14
    Condensed
    1.14
     कीमतें
    1.14
    രക്ഷ
    1.09
    Standalone
    1.07
     confesses
    1.07
    𝙞
    1.05
     predisposition
    1.05
    ities
    1.04
    临
    1.04
    Activations Density 0.001%

    No Known Activations