© 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. 143052
    Prev
    Next
    INDEX
    Explanations

    Records data streams

    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
    䡆
    0.47
     stints
    0.47
     Negotiations
    0.46
     Hosted
    0.46
    hosting
    0.45
    在全球
    0.45
     Agreements
    0.44
    䨐
    0.44
    ผ่าน
    0.44
     Merchandise
    0.44
    POSITIVE LOGITS
    ası
    0.46
    4
    0.46
     polin
    0.45
    5
    0.45
    ⵡ
    0.44
    Manifest
    0.43
    3
    0.42
     dies
    0.42
     decim
    0.41
    AMP
    0.41
    Activations Density 0.000%

    No Known Activations