Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 5112
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns/adjectives

    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
     without
    0.40
    一些
    0.38
     বেশকিছু
    0.38
     well
    0.36
    नई
    0.36
    এক
    0.35
     as
    0.35
    '):
    0.35
    টিও
    0.35
    ২
    0.34
    POSITIVE LOGITS
     this
    0.53
     aceste
    0.50
     questa
    0.49
    該
    0.49
     этих
    0.48
     queste
    0.47
     wannan
    0.47
     questo
    0.46
     diesem
    0.45
     these
    0.44
    Activations Density 0.219%

    No Known Activations