© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 184375
    Prev
    Next
    INDEX
    Explanations

    shadow, writers, leaders

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

    exploit injection attacks

    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
    el
    0.45
    eed
    0.45
    쭉
    0.44
     boul
    0.42
    elina
    0.41
     Task
    0.41
    ادو
    0.41
     Managed
    0.41
    琪
    0.41
    zada
    0.40
    POSITIVE LOGITS
     убе
    0.48
     whence
    0.48
     verify
    0.47
    mt
    0.47
    ြ
    0.47
     convincing
    0.47
    larınız
    0.46
    を作る
    0.45
     mT
    0.45
     orbifold
    0.45
    Activations Density 0.001%

    No Known Activations