Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 12665
    Prev
    Next
    INDEX
    Explanations

    in or on phrases

    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
    ed
    0.46
    in
    0.38
    ing
    0.38
    ة
    0.38
     protección
    0.37
    ilo
    0.36
    有效地
    0.36
    あ
    0.36
     trochę
    0.35
    ը
    0.35
    POSITIVE LOGITS
     matériaux
    0.43
    自身
    0.42
     oneself
    0.42
     해당
    0.40
    事項
    0.39
     인한
    0.38
    贋
    0.38
     Materialien
    0.38
     externalities
    0.37
     volatiles
    0.36
    Activations Density 0.028%

    No Known Activations