© 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. 83863
    Prev
    Next
    INDEX
    Explanations

    admin mode

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

    script tag endings, marital property

    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
    elevation
    0.53
    обре
    0.52
    hôte
    0.52
    📔
    0.50
     siècle
    0.50
     சிற்ப
    0.48
    🍝
    0.48
    代
    0.48
    мя
    0.47
     также
    0.47
    POSITIVE LOGITS
    සර
    0.49
     ness
    0.45
    arters
    0.44
     opioid
    0.44
     truthful
    0.43
     stares
    0.43
     applic
    0.42
     necessities
    0.41
     means
    0.41
     safer
    0.40
    Activations Density 0.002%

    No Known Activations