© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 110822
    Prev
    Next
    INDEX
    Explanations

    adjectives followed by nouns

    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
     शुभारंभ
    0.41
    넥
    0.40
     *}\
    0.39
     $\$
    0.38
     졸
    0.37
     परिचाल
    0.37
    Causes
    0.37
     인터넷
    0.37
    nau
    0.36
    객
    0.36
    POSITIVE LOGITS
     phá
    0.39
    voj
    0.39
    dump
    0.38
    лож
    0.37
     thickly
    0.36
    ……..
    0.36
     vários
    0.35
     দেশে
    0.35
     rende
    0.35
    墳
    0.35
    Activations Density 0.000%

    No Known Activations