© 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. 34659
    Prev
    Next
    INDEX
    Explanations

    must adhere

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

    existence, risk, and opinion

    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
    ím
    0.54
    íp
    0.52
    ън
    0.50
    ين
    0.47
    <0x0D>
    0.47
    াদ
    0.46
     ED
    0.46
    án
    0.46
     Defender
    0.46
    सी
    0.45
    POSITIVE LOGITS
     அதாவது
    0.57
     کرکے
    0.52
    تهم
    0.52
    تمد
    0.51
     करण्यास
    0.51
    arei
    0.50
     перший
    0.50
     போ
    0.50
     тара
    0.49
     viciss
    0.48
    Activations Density 0.000%

    No Known Activations