© 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. 11
    Prev
    Next
    INDEX
    Explanations

    adverbial suffixes and words ending in -able/-ible

    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
    ارهای
    0.42
    orgement
    0.40
     TOOL
    0.40
    сування
    0.38
    োষণ
    0.38
    愘
    0.38
     BSData
    0.38
    дування
    0.37
    梸
    0.37
    গুলোতে
    0.37
    POSITIVE LOGITS
    edly
    0.44
    ly
    0.43
    的に
    0.42
    it
    0.40
    ingly
    0.39
    adamente
    0.38
    적으로
    0.36
    ed
    0.35
    entemente
    0.35
    itably
    0.32
    Activations Density 0.061%

    No Known Activations