© 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. 65474
    Prev
    Next
    INDEX
    Explanations

    global leader or corporation

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

    used in definitions

    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
    𝔹
    0.48
    ნ
    0.44
     let
    0.44
    共和国
    0.43
    Pet
    0.43
     UM
    0.43
    ه‌ی
    0.43
    的速度
    0.43
    自然的
    0.43
    å
    0.42
    POSITIVE LOGITS
     posuere
    0.47
    舘
    0.46
     sylvis
    0.45
    zzo
    0.44
     interstitiis
    0.44
    calar
    0.43
    দ্দিন
    0.42
     ethan
    0.42
    pload
    0.42
     ಕರಿ
    0.42
    Activations Density 0.000%

    No Known Activations