© 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-262K
    7. 123443
    Prev
    Next
    INDEX
    Explanations

    adjective noun pairings

    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_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
     довольно
    0.41
     соору
    0.41
     செ
    0.40
     belongings
    0.39
     скорее
    0.38
     যতক্ষণ
    0.38
     αποτέ
    0.38
     е
    0.37
    ཎ
    0.37
     लेख
    0.36
    POSITIVE LOGITS
    ｙ
    0.46
     ආකාර
    0.45
    ｊ
    0.44
    speak
    0.42
    JP
    0.40
    pada
    0.40
     أنواع
    0.39
    Jay
    0.38
    cannot
    0.38
    travel
    0.38
    Activations Density 0.068%

    No Known Activations