© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1598
    Prev
    Next
    INDEX
    Explanations

    possessive 's contractions

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

    apostrophes within words

    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
     \"
    0.40
     $\
    0.36
     $=$
    0.36
     $(
    0.36
     $*$
    0.35
     $-$
    0.35
     $=\
    0.34
     तथा
    0.34
     כאשר
    0.34
     ${
    0.34
    POSITIVE LOGITS
     crappy
    0.38
    ...”
    0.37
     Couldn
    0.34
    了我
    0.34
     shitty
    0.32
    didn
    0.32
    Honestly
    0.31
    I
    0.30
    ‍
    0.30
    ishy
    0.30
    Activations Density 0.629%

    No Known Activations