© 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-262K
    7. 3952
    Prev
    Next
    INDEX
    Explanations

    past performance disclaimer

    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
    кте
    1.33
     fatti
    1.31
    DateTimeField
    1.28
     jazdy
    1.26
     secondNumber
    1.26
     查询
    1.26
    ቑ
    1.23
     CDKN
    1.22
    ╾
    1.21
    葚
    1.21
    POSITIVE LOGITS
     बढ़ाकर
    0.89
     macer
    0.89
     checking
    0.82
    plastic
    0.81
     check
    0.80
     successful
    0.79
     достига
    0.79
    BATCH
    0.78
     yarns
    0.77
    +
    0.77
    Activations Density 0.001%

    No Known Activations