© 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. 53-GEMMASCOPE-2-RES-262K
    7. 34206
    Prev
    Next
    INDEX
    Explanations

    supposedly / 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_53_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
     unwelcome
    0.45
     arguably
    0.43
    𝘏
    0.43
    }}^{(\
    0.40
    並不
    0.40
     également
    0.39
     persistently
    0.39
    $(\
    0.39
     específico
    0.38
     കൂ
    0.38
    POSITIVE LOGITS
     якобы
    1.23
     supposedly
    1.16
     blah
    0.96
     purportedly
    0.93
     allegedly
    0.91
     নাকি
    0.85
     údaj
    0.81
     unspecified
    0.80
     magically
    0.79
     somehow
    0.71
    Activations Density 0.052%

    No Known Activations