© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17573
    Prev
    Next
    INDEX
    Explanations

    mottos, slogans, and adages

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

    slogans, sayings, and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    streetmap
    0.35
     disclosed
    0.34
     &=\
    0.34
    roff
    0.34
    െങ്ക
    0.33
     ورق
    0.33
    ="../../../
    0.33
     grazed
    0.33
     extraction
    0.33
    㳓
    0.33
    POSITIVE LOGITS
     slogan
    2.67
     motto
    2.63
     proverb
    2.58
     adage
    2.42
     Motto
    2.28
     slogans
    2.20
     mantra
    2.13
     saying
    2.06
     tagline
    2.02
     sayings
    1.99
    Activations Density 0.170%

    No Known Activations