© 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. 13908
    Prev
    Next
    INDEX
    Explanations

    litters, escape, looking, offer

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

    numbers and quantities

    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
     we
    0.51
    1
    0.48
    4
    0.48
    &
    0.46
     as
    0.45
     described
    0.45
     are
    0.45
    0.43
     shared
    0.42
     he
    0.42
    POSITIVE LOGITS
    တတ်
    0.54
    曷
    0.52
     легче
    0.50
    境界層
    0.50
    傗
    0.49
    Якщо
    0.49
    เมื่อ
    0.47
     వల్ల
    0.47
    𒌝
    0.46
    விட்டால்
    0.46
    Activations Density 0.000%

    No Known Activations