© 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-65K
    7. 3770
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and participles

    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_65k_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
     год
    0.44
     tahun
    0.44
    }^{-}\
    0.42
    يتها
    0.42
     jaar
    0.41
     jednom
    0.41
    nin
    0.40
     رحمه
    0.40
     ১৯৬৫
    0.40
     on
    0.40
    POSITIVE LOGITS
     cooled
    0.38
     accentuated
    0.37
    শিষ্ট
    0.37
     braced
    0.37
     calc
    0.36
     Heated
    0.36
    あい
    0.36
    ூ
    0.36
    ိုက်
    0.35
     ಕೂಡ
    0.35
    Activations Density 0.003%

    No Known Activations