© 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-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 377
    Prev
    Next
    INDEX
    Explanations

    Companies are adapting

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

    mentions of groups in the plural—especially collective references to people or organizations (plural nouns, pronouns, or quantifiers indicating many).

    oai_token-act-pair · gpt-5Triggered by @smilgaveronika
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_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
    was
    1.37
     связано
    1.37
    Was
    1.31
     било
    1.28
     заключается
    1.27
    шел
    1.23
    ходила
    1.23
    шёл
    1.22
     относится
    1.21
     شود
    1.20
    POSITIVE LOGITS
     are
    2.78
    都有
    2.47
     aren
    2.38
    都很
    2.33
    都在
    2.29
     đều
    2.27
     hanno
    2.24
    都会
    2.23
     هستند
    2.22
     precisam
    2.21
    Activations Density 2.480%

    No Known Activations