© 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. 117226
    Prev
    Next
    INDEX
    Explanations

    get maps

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

    conveys one or more specific targets

    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
    Ko
    0.46
    ots
    0.46
     Maire
    0.45
     royalty
    0.45
    ville
    0.44
    -
    0.44
     &
    0.42
     sovereignty
    0.42
     Greta
    0.42
     masking
    0.42
    POSITIVE LOGITS
     तमाम
    0.46
     многочис
    0.46
    糈
    0.45
    findAll
    0.44
     молодо
    0.44
    dür
    0.44
     букме
    0.44
     தருக
    0.43
    なのに
    0.43
     rů
    0.42
    Activations Density 0.001%

    No Known Activations