© 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. 123080
    Prev
    Next
    INDEX
    Explanations

    debugging easier

    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
    ના
    0.51
     provoque
    0.51
    ∆
    0.50
     borrow
    0.48
    of
    0.48
    ござ
    0.46
    uksi
    0.45
    の話
    0.44
    vient
    0.44
    have
    0.43
    POSITIVE LOGITS
    y
    0.48
    ophylline
    0.46
    givers
    0.46
     पारदर्शिता
    0.46
    チル
    0.44
    疗
    0.44
    𝐲
    0.44
    retching
    0.43
     isomorphisms
    0.42
     διάρκ
    0.41
    Activations Density 0.004%

    No Known Activations