© 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. 40644
    Prev
    Next
    INDEX
    Explanations

    positive outcomes and descriptions

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

    social media content or technical descriptions

    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
    ئ
    0.61
    ne
    0.57
    ty
    0.57
    ت
    0.55
    detailed
    0.53
    ة
    0.53
     سه
    0.47
    t
    0.47
    ut
    0.47
    ্য
    0.46
    POSITIVE LOGITS
     deix
    0.52
     verilen
    0.50
     admitting
    0.49
    假期
    0.49
     viernes
    0.49
     revisiting
    0.49
     admite
    0.49
     గుర్తు
    0.48
     semoga
    0.47
     vendredi
    0.47
    Activations Density 0.000%

    No Known Activations