© 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. 157650
    Prev
    Next
    INDEX
    Explanations

    URLs containing "content"

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

    parts of phrases

    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
    <unused22>
    0.60
    󰡕
    0.58
    ریع
    0.57
     dhinak
    0.57
    AOrdenar
    0.57
    мії
    0.56
     дипло
    0.56
    𒊑
    0.55
     рит
    0.55
    дт
    0.55
    POSITIVE LOGITS
    in
    0.70
     K
    0.68
     P
    0.65
    ids
    0.65
    0.64
     T
    0.62
    h
    0.60
     o
    0.60
    u
    0.59
    c
    0.57
    Activations Density 0.000%

    No Known Activations