© 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-16K
    7. 12003
    Prev
    Next
    INDEX
    Explanations

    code structure keywords

    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
    Dropdown
    0.38
    풀
    0.38
    dropdown
    0.37
     frivolous
    0.37
    logrus
    0.36
    NewLine
    0.36
    AssetsRequest
    0.35
    healing
    0.35
    훌
    0.35
     আগ
    0.34
    POSITIVE LOGITS
    orar
    0.45
     knows
    0.43
     Knows
    0.42
    ARIO
    0.41
    ARIOS
    0.39
     viss
    0.38
    arios
    0.37
     vivos
    0.37
     vécu
    0.36
     médicos
    0.36
    Activations Density 0.164%

    No Known Activations