© 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. 45519
    Prev
    Next
    INDEX
    Explanations

    growing awarded state determines

    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
    啟
    0.42
    ండో
    0.41
    霜
    0.41
    MIER
    0.40
     okam
    0.39
     chicken
    0.38
     kolo
    0.38
    ణ
    0.38
    ಮ್ಮೆ
    0.38
    ทด
    0.37
    POSITIVE LOGITS
     also
    0.48
     también
    0.47
     также
    0.44
     também
    0.43
     amassed
    0.42
     ఉన్న
    0.42
    also
    0.42
    послед
    0.42
     również
    0.41
     myös
    0.41
    Activations Density 0.001%

    No Known Activations