© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101465
    Prev
    Next
    INDEX
    Explanations

    phishing and iterative refinement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     грун
    0.44
    ድረ
    0.43
    🗒
    0.43
     internals
    0.42
     separation
    0.42
     imputation
    0.41
    🤧
    0.41
    かれて
    0.41
    な
    0.40
    いません
    0.40
    POSITIVE LOGITS
    为其
    0.47
     Catalina
    0.45
     mayoría
    0.44
    ianza
    0.43
    ía
    0.42
    TER
    0.41
    Proyecto
    0.40
     Projek
    0.40
     शर्त
    0.39
     Triton
    0.39
    Activations Density 0.002%

    No Known Activations