© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4685
    Prev
    Next
    INDEX
    Explanations

    words ending in -ence, -tion, -rection

    np_acts-logits-general · gemini-2.5-flash-lite

    word endings like tion ence able

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ভয়ঙ্কর
    0.44
     purnama
    0.41
    ⟋
    0.40
     dezembro
    0.39
     modalCard
    0.39
    yyati
    0.38
    বিষ্ট
    0.38
    鈿
    0.38
    䔬
    0.38
    <unused1030>
    0.37
    POSITIVE LOGITS
    tions
    0.75
    ition
    0.73
    ccess
    0.71
    ction
    0.69
    tion
    0.68
    tional
    0.66
    nce
    0.64
    nt
    0.64
    rt
    0.64
     recieved
    0.64
    Activations Density 0.324%

    No Known Activations