© 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. 24031
    Prev
    Next
    INDEX
    Explanations

    aperture stop, security services, market researcher

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

    often before time or descriptive terms

    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
     मौखिक
    0.52
     Subtle
    0.50
     इमारत
    0.48
    旂
    0.46
    ılım
    0.46
     Podcasts
    0.46
    淆
    0.46
    Տ
    0.45
     Elements
    0.45
    Į
    0.45
    POSITIVE LOGITS
     concours
    0.58
    February
    0.52
     expense
    0.52
    March
    0.49
     adjudged
    0.48
    тинен
    0.48
     marché
    0.47
     conséqu
    0.47
    expense
    0.47
    for
    0.45
    Activations Density 0.000%

    No Known Activations