© 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. 202872
    Prev
    Next
    INDEX
    Explanations

    finding numbered lists

    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
    IAN
    0.49
    Antes
    0.47
     antes
    0.45
    Los
    0.45
     questa
    0.44
    ต
    0.43
    亿美元
    0.42
     gira
    0.42
     goles
    0.42
    ب
    0.42
    POSITIVE LOGITS
    nahmen
    0.55
    nahme
    0.46
    haha
    0.45
    keme
    0.45
     OSI
    0.44
    millan
    0.44
    nimmt
    0.44
    ోధ
    0.44
    ouville
    0.43
    chre
    0.43
    Activations Density 0.002%

    No Known Activations