© 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. 9160
    Prev
    Next
    INDEX
    Explanations

    Spanish language movie awards

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

    years and bios

    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
    🥰
    1.32
     🥰
    1.23
     ২০২২
    1.20
    🥳
    1.20
    🥲
    1.20
    🫶
    1.17
    🥹
    1.13
    🥺
    1.12
    🤍
    1.09
    🤭
    1.09
    POSITIVE LOGITS
     ২০১৫
    1.41
     ২০১৪
    1.34
     Ebola
    1.16
     २०१
    1.10
     ২০১৩
    1.02
     Huffington
    1.02
    http
    0.94
     http
    0.91
     xrange
    0.91
     ২০১৬
    0.89
    Activations Density 0.572%

    No Known Activations