© 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. 40336
    Prev
    Next
    INDEX
    Explanations

    providing a high-quality service

    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
     用于
    0.46
     safeguard
    0.45
     предназна
    0.43
    🧴
    0.43
     为
    0.43
     źród
    0.42
     為
    0.42
    用於
    0.41
     source
    0.40
     bagi
    0.39
    POSITIVE LOGITS
    is
    0.43
     superb
    0.42
    accurate
    0.42
     comprehensive
    0.42
    realistic
    0.40
     полный
    0.39
     realistic
    0.39
     umfass
    0.39
     excellent
    0.38
     truly
    0.38
    Activations Density 0.040%

    No Known Activations