© 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. 201880
    Prev
    Next
    INDEX
    Explanations

    preparing for update

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

    risks, competition, unstable

    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
    ▪
    0.47
     Westwood
    0.45
     actual
    0.44
    이면
    0.43
    Label
    0.42
    ❤
    0.42
    발
    0.42
     ■
    0.41
    ውን
    0.41
     hy
    0.41
    POSITIVE LOGITS
     titik
    0.56
     enerji
    0.54
     چې
    0.51
     زائد
    0.50
     amelyek
    0.50
     které
    0.49
     energética
    0.49
     فه
    0.47
     tattha
    0.47
     चट
    0.47
    Activations Density 0.002%

    No Known Activations