© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 138269
    Prev
    Next
    INDEX
    Explanations

    comparing models (Gemma, GPT4All, Bard)

    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
    <0x86>
    0.50
     Ú
    0.49
     ее
    0.48
     её
    0.46
     її
    0.46
    anilide
    0.45
    хан
    0.45
     Ψ
    0.44
    ユ
    0.44
     остальные
    0.43
    POSITIVE LOGITS
     bookmarks
    0.45
     depicts
    0.44
    借鉴
    0.44
    Stephen
    0.43
     riffs
    0.43
     calendars
    0.42
     ফেব্রুয়ার
    0.42
     sees
    0.41
     disc
    0.41
     sermons
    0.41
    Activations Density 0.007%

    No Known Activations