© 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-16K
    4. 13808
    Prev
    Next
    INDEX
    Explanations

    pieces and snippets

    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_16k_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
     the
    0.65
    es
    0.64
    PL
    0.64
    S
    0.63
    F
    0.63
    e
    0.60
    ish
    0.59
    B
    0.59
    u
    0.58
    </strong>
    0.58
    POSITIVE LOGITS
     кусо
    1.05
    片段
    0.96
     fragments
    0.93
     قطعة
    0.93
     pieces
    0.92
     टुकड़े
    0.91
     фраг
    0.87
     fragment
    0.86
     chunks
    0.84
     snippets
    0.84
    Activations Density 0.290%

    No Known Activations