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. 1016
    Prev
    Next
    INDEX
    Explanations

    "so" and "such" as intensifiers

    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
    on
    0.59
    و
    0.52
    r
    0.51
    y
    0.49
    P
    0.44
     Veamos
    0.43
     također
    0.42
     Preferably
    0.42
    ad
    0.41
    S
    0.41
    POSITIVE LOGITS
     tantas
    0.69
     এত
    0.68
     unbelievably
    0.66
     tellement
    0.65
     इतने
    0.63
     soooo
    0.63
     tantos
    0.63
     incrível
    0.60
     unglaublich
    0.60
    那么多
    0.59
    Activations Density 0.031%

    No Known Activations