© 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. 40-GEMMASCOPE-2-RES-262K
    7. 13851
    Prev
    Next
    INDEX
    Explanations

    lines and lined paper

    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
     zroz
    0.43
     rental
    0.43
     typology
    0.41
     expr
    0.41
     pubb
    0.41
     aliases
    0.40
     ሲ
    0.40
     opcode
    0.39
    Ỡ
    0.39
     URI
    0.39
    POSITIVE LOGITS
    Lines
    1.13
     lines
    1.10
    lines
    1.09
    Line
    1.05
     Lines
    1.03
     lined
    1.00
     líneas
    1.00
    line
    0.98
     line
    0.96
     линий
    0.95
    Activations Density 0.003%

    No Known Activations