© 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. 116359
    Prev
    Next
    INDEX
    Explanations

    future opportunities and actions

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

    critical infrastructure and AI

    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
     have
    0.52
    祸
    0.43
     an
    0.43
    ated
    0.43
    ズニー
    0.42
     occupation
    0.41
     had
    0.41
     dungeon
    0.41
    ….
    0.40
     vẫn
    0.40
    POSITIVE LOGITS
     FULLER
    0.51
    𝘦
    0.50
    टाम
    0.47
    ₸
    0.47
    𝓼
    0.47
    鯱
    0.46
    வார்கள்
    0.46
    ᔕ
    0.46
    MSFontService
    0.45
     WHICH
    0.45
    Activations Density 0.001%

    No Known Activations