© 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. 40-GEMMASCOPE-2-RES-262K
    7. 131
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions

    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_40_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
     âgé
    0.34
    èvres
    0.33
     gdyż
    0.32
     તરીકે
    0.31
    på
    0.31
    opod
    0.30
     wobei
    0.30
    㗎
    0.30
    ovací
    0.29
    étais
    0.29
    POSITIVE LOGITS
     उन
    0.40
     tp
    0.40
    䏹
    0.39
    <unused2171>
    0.39
     vaan
    0.39
     foro
    0.37
     anecdotal
    0.37
    于
    0.35
     عن
    0.35
    过去了
    0.35
    Activations Density 0.216%

    No Known Activations