© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 204622
    Prev
    Next
    INDEX
    Explanations

    describing media, actions, or states

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

    automated answering

    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
    éments
    0.52
    Marshaler
    0.49
    amaks
    0.48
     фигур
    0.48
    挀
    0.48
     பார்க்கலாம்
    0.48
     kanyang
    0.47
    ැල
    0.46
    फ्त
    0.46
     애
    0.46
    POSITIVE LOGITS
     demonstrable
    0.46
     accountability
    0.45
     Prav
    0.45
     play
    0.44
     elucidation
    0.44
     paradig
    0.44
    -
    0.44
    在前
    0.43
     exalt
    0.43
    身高
    0.43
    Activations Density 0.000%

    No Known Activations