© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 469
    Prev
    Next
    INDEX
    Explanations

    council, arguably

    np_acts-logits-general · gemini-2.5-flash-lite

    absence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BOTH
    0.41
     &/
    0.40
     혹은
    0.40
     deberá
    0.39
    }^{
    0.39
     אך
    0.38
     पश्चात
    0.38
     murderous
    0.38
    }(\
    0.38
     মোঃ
    0.37
    POSITIVE LOGITS
    すごく
    0.54
     ahorita
    0.50
     väldigt
    0.48
     people
    0.47
     굉장히
    0.47
     everybody
    0.46
     veldig
    0.46
    people
    0.45
    いろんな
    0.45
     लोगों
    0.44
    Activations Density 0.325%

    No Known Activations