© 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. 248
    Prev
    Next
    INDEX
    Explanations

    federal and political news

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

    link separators and subsequent content

    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
     posiada
    0.41
     존재하는
    0.39
    垛
    0.39
     skall
    0.39
     operazioni
    0.39
     elucid
    0.38
     herhangi
    0.38
     dimensionality
    0.38
     wastage
    0.37
     glPushMatrix
    0.37
    POSITIVE LOGITS
    Bloomberg
    0.56
     Bloomberg
    0.48
    nytimes
    0.46
     nonprofits
    0.45
    聽
    0.45
     federal
    0.43
     spokeswoman
    0.42
    WASHINGTON
    0.42
     lawmakers
    0.41
     lawmaker
    0.41
    Activations Density 0.265%

    No Known Activations