© 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. 40-GEMMASCOPE-2-RES-262K
    4. 133265
    Prev
    Next
    INDEX
    Explanations

    cybersecurity, dreams, self, sticky, garlic, increasing, clinic

    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_40_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
    ÁS
    0.42
    #![
    0.42
    MORE
    0.39
    ાઇ
    0.38
    ને
    0.38
     décoration
    0.38
    Capitol
    0.38
    വ
    0.36
     प्रकोप
    0.36
    uste
    0.35
    POSITIVE LOGITS
     consulta
    0.44
     quart
    0.44
     kw
    0.43
     ocorre
    0.42
     subordin
    0.42
     Watts
    0.41
     resposta
    0.41
     depending
    0.40
     निर्धारित
    0.40
     Ports
    0.39
    Activations Density 0.000%

    No Known Activations