© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 204438
    Prev
    Next
    INDEX
    Explanations

    parsing code and descriptions

    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
    ORGE
    0.38
     माहित
    0.38
    ্রয়
    0.38
    finder
    0.36
    GLISH
    0.36
    icially
    0.36
    rologist
    0.36
     습
    0.36
     ISR
    0.36
     তলায়
    0.36
    POSITIVE LOGITS
    երը
    0.44
     negatif
    0.39
    เอก
    0.39
     positivas
    0.39
     recreate
    0.38
    viridis
    0.38
     setups
    0.38
     cesse
    0.38
     parthenogenetic
    0.38
     dxc
    0.37
    Activations Density 0.000%

    No Known Activations