© 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. 31-GEMMASCOPE-2-RES-262K
    7. 19248
    Prev
    Next
    INDEX
    Explanations

    County: or first King

    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_31_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
    AsString
    0.46
    ifices
    0.46
    streetlight
    0.45
    امر
    0.45
    ClFN
    0.45
    mlst
    0.43
    涩
    0.43
     प्रमाणात
    0.42
    cfp
    0.42
    alchemy
    0.42
    POSITIVE LOGITS
     mens
    0.47
     house
    0.42
     broad
    0.42
    ’
    0.41
     hobbies
    0.41
     {
    0.41
     hemen
    0.41
     and
    0.41
     heck
    0.40
     big
    0.39
    Activations Density 0.001%

    No Known Activations