© 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. 11687
    Prev
    Next
    INDEX
    Explanations

    hundreds of millions

    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
    :=
    0.79
     метою
    0.74
    地址
    0.74
    :=\
    0.74
    getStudentNo
    0.72
     để
    0.72
    Samsung
    0.71
     :=
    0.70
    Delay
    0.69
     nhằm
    0.69
    POSITIVE LOGITS
     hundreds
    1.14
     thousands
    1.14
     billions
    1.10
     millions
    1.05
     thousand
    0.97
     trillions
    0.97
     quizzes
    0.97
     magazines
    0.96
     quiz
    0.94
     dozens
    0.93
    Activations Density 0.000%

    No Known Activations