© 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. 110935
    Prev
    Next
    INDEX
    Explanations

    investors guided, brochure template

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

    oversaw, handled, freedom, individual

    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
     uncovering
    0.49
     احتجاج
    0.48
     importantes
    0.46
    ۲
    0.45
     OnTrigger
    0.45
    SUFF
    0.42
     suspicion
    0.41
    Uninstall
    0.41
     Uninstall
    0.41
     inappropri
    0.41
    POSITIVE LOGITS
    мости
    0.50
    λού
    0.50
     脚
    0.46
    вшихся
    0.46
     persone
    0.46
    বন
    0.46
    μος
    0.46
    resized
    0.44
     复
    0.44
    ъ
    0.43
    Activations Density 0.001%

    No Known Activations