© 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. 31-GEMMASCOPE-2-RES-262K
    7. 6822
    Prev
    Next
    INDEX
    Explanations

    noun followed by related noun

    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
    ارهای
    0.41
    urgical
    0.36
     முடியாத
    0.36
    齙
    0.36
    bär
    0.35
    പ്പെടുന്ന
    0.34
     années
    0.33
    üü
    0.33
    የ
    0.33
    糇
    0.33
    POSITIVE LOGITS
     واع
    0.37
    .”
    0.33
    𒐪
    0.33
     fortæ
    0.32
    }$.
    0.32
     क्योंकि
    0.31
     onlook
    0.31
     wors
    0.31
    respond
    0.31
     जैसा
    0.30
    Activations Density 0.653%

    No Known Activations