© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 168151
    Prev
    Next
    INDEX
    Explanations

    Amazon SQS Queue

    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_40_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
    Deque
    0.43
    gher
    0.43
    奸
    0.42
    aturan
    0.41
    দেখে
    0.40
    姦
    0.39
    taste
    0.39
    Dise
    0.38
    Imagem
    0.38
    Template
    0.37
    POSITIVE LOGITS
    住宿
    0.38
    ത്
    0.38
     solic
    0.38
    榃
    0.37
    etically
    0.37
     housewife
    0.37
    疙
    0.37
     incidents
    0.37
     nonetheless
    0.37
     Ernesto
    0.37
    Activations Density 0.000%

    No Known Activations