© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8680
    Prev
    Next
    INDEX
    Explanations

    parts of speech, rare words

    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
     Alla
    0.45
     puisque
    0.45
     γιατί
    0.44
     Kanji
    0.42
    先生
    0.42
     заменить
    0.41
    Sau
    0.41
    삵
    0.41
    uyentes
    0.40
     buoni
    0.40
    POSITIVE LOGITS
     rarely
    0.52
    noun
    0.46
     noun
    0.46
     rarity
    0.44
     increasingly
    0.44
     metaphorical
    0.44
     archaic
    0.44
     architectural
    0.43
     mythological
    0.43
     rare
    0.43
    Activations Density 0.112%

    No Known Activations