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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 36047
    Prev
    Next
    INDEX
    Explanations

    still / continuation

    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
    Soon
    0.43
     Soon
    0.42
    弇
    0.40
     toekom
    0.40
    soon
    0.40
    ंपरिक
    0.39
     применять
    0.38
    getOutputStream
    0.37
    𝒾
    0.37
     заранее
    0.37
    POSITIVE LOGITS
     still
    1.52
     STILL
    1.49
    still
    1.41
     fortfarande
    1.38
    仍然
    1.34
    仍
    1.34
    Still
    1.32
    依然
    1.31
     Still
    1.30
     vẫn
    1.27
    Activations Density 0.026%

    No Known Activations