© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11086
    Prev
    Next
    INDEX
    Explanations

    FW: emails and links

    np_acts-logits-general · gemini-2.5-flash-lite

    the abbreviation "FW" (forward) in email headers and technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -4.19
     reputable
    -2.77
    灩
    -2.58
     \
    -2.53
    肫
    -2.34
    艫
    -2.30
     única
    -2.28
    戩
    -2.28
    蹀
    -2.25
    鲀
    -2.20
    POSITIVE LOGITS
    櫚
    2.66
    '
    2.38
    ….”
    2.28
    ya
    2.23
    fw
    2.22
    にい
    2.11
     outspoken
    2.09
    ulism
    2.08
    elerik
    2.03
    鲠
    2.03
    Activations Density 0.003%

    No Known Activations