© 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. 194020
    Prev
    Next
    INDEX
    Explanations

    police and cared

    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
    imag
    0.41
    adou
    0.39
    ்க
    0.38
    Imag
    0.37
     seem
    0.36
    简
    0.36
     McClure
    0.36
    ador
    0.36
    ես
    0.35
    κή
    0.35
    POSITIVE LOGITS
     తెలిప
    0.48
     Wings
    0.47
    ਅ
    0.45
    மாவட்ட
    0.45
     Tanz
    0.44
     Nell
    0.42
     Vegan
    0.41
     Sling
    0.41
     Bla
    0.41
     pf
    0.41
    Activations Density 0.000%

    No Known Activations