© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28609
    Prev
    Next
    INDEX
    Explanations

    pronoun/noun followed by verb/noun

    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_262k_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
     situazione
    0.47
     situations
    0.46
     exertion
    0.44
    ﻞ
    0.44
     situações
    0.44
     specifica
    0.44
     juxtaposition
    0.44
     ವಿಧಾನ
    0.43
    ্ষিকী
    0.43
     situação
    0.43
    POSITIVE LOGITS
    ʼ
    0.47
     Surprisingly
    0.46
    ..(
    0.46
     REALLY
    0.45
     Damn
    0.44
     Actually
    0.44
     wasn
    0.43
     あなた
    0.43
     Didn
    0.43
     forgot
    0.42
    Activations Density 0.047%

    No Known Activations