© 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. 189980
    Prev
    Next
    INDEX
    Explanations

    sophisticated completion

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

    creating your, here to, safe for

    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
    衽
    0.61
     pretends
    0.52
    ード
    0.51
    ྵ
    0.50
    ев
    0.50
    innerApiCalls
    0.49
    πει
    0.49
    提出
    0.48
    杼
    0.48
    讒
    0.48
    POSITIVE LOGITS
    u
    0.57
    at
    0.50
     Lupus
    0.50
    ut
    0.48
    <0x0D>
    0.48
    azier
    0.47
     da
    0.47
     Story
    0.47
     Rica
    0.46
     Lug
    0.46
    Activations Density 0.000%

    No Known Activations