© 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. 73746
    Prev
    Next
    INDEX
    Explanations

    in [context/state]

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

    strategies, objectives, capabilities

    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
    ramework
    0.47
    ліза
    0.43
     ถาม
    0.42
     katva
    0.42
    న్
    0.42
     क्वे
    0.42
    梼
    0.42
    Ř
    0.41
    ্রো
    0.39
    㐬
    0.39
    POSITIVE LOGITS
     AP
    0.43
     ENGLAND
    0.42
    تهي
    0.42
     esta
    0.42
    isLoading
    0.41
     an
    0.41
     iba
    0.41
     intitulé
    0.41
     barges
    0.41
     his
    0.41
    Activations Density 0.001%

    No Known Activations