© 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. 122893
    Prev
    Next
    INDEX
    Explanations

    capture

    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
    ㍉
    0.50
     silvest
    0.47
    نا
    0.43
    йся
    0.42
    ।”
    0.41
     patchy
    0.41
     Floyd
    0.40
    ᐋ
    0.40
    ്രീ
    0.40
    ură
    0.40
    POSITIVE LOGITS
     leftmost
    0.54
     preference
    0.45
     первые
    0.44
    aces
    0.43
     astrophys
    0.43
    一个个
    0.43
     பின்னர்
    0.42
    omb
    0.42
     Preference
    0.41
    眼前
    0.41
    Activations Density 0.009%

    No Known Activations