© 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. 3744
    Prev
    Next
    INDEX
    Explanations

    ostensibly, supposedly, purportedly, allegedly

    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
     hochwertige
    0.42
     trusty
    0.41
     هيكون
    0.38
     izango
    0.38
    രിക്കും
    0.38
    𝕌
    0.37
     będ
    0.37
     będzie
    0.37
     zuverläss
    0.37
    \
    0.37
    POSITIVE LOGITS
     ostensibly
    0.89
     supposedly
    0.87
     якобы
    0.82
     purportedly
    0.82
     allegedly
    0.80
     purported
    0.72
     aparentemente
    0.70
     apparently
    0.69
     seemingly
    0.69
     कथित
    0.68
    Activations Density 0.122%

    No Known Activations