© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 34912
    Prev
    Next
    INDEX
    Explanations

    code logic and math concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     качественно
    0.36
    নকে
    0.34
     nghĩa
    0.33
    ᄌ
    0.32
     आपका
    0.32
     самым
    0.32
    міст
    0.32
     سلاٹس
    0.31
    ALK
    0.31
    顽
    0.31
    POSITIVE LOGITS
    atin
    0.45
    ata
    0.44
    ander
    0.42
    ato
    0.41
    ethod
    0.41
    aren
    0.40
    ble
    0.40
      
    0.38
    ated
    0.38
    ys
    0.38
    Activations Density 0.034%

    No Known Activations