© 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-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 11804
    Prev
    Next
    INDEX
    Explanations

    connecting clauses and lists

    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_31_width_65k_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
    !
    0.37
    �
    0.34
    .
    0.33
    <0x0D>
    0.32
     .
    0.32
    ."
    0.31
    .”
    0.31
     Pl
    0.31
    !"
    0.31
    сь
    0.30
    POSITIVE LOGITS
    ರುವುದರಿಂದ
    0.52
    していますが
    0.47
     இருப்பதால்
    0.46
    しているので
    0.45
     그다음에
    0.42
     ಮತ್ತು
    0.42
     없고
    0.41
    と思いますが
    0.40
    puede
    0.40
    insieme
    0.39
    Activations Density 0.095%

    No Known Activations