© 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. 16-GEMMASCOPE-2-RES-262K
    7. 1427
    Prev
    Next
    INDEX
    Explanations

    contraction and possessive markers

    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_16_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
    ุ
    0.60
     metodologia
    0.53
    ெ
    0.53
    עי
    0.52
    சாக
    0.49
     POINTS
    0.48
     फंडा
    0.48
     notor
    0.48
    ناول
    0.48
     इंग्लंड
    0.48
    POSITIVE LOGITS
    畏
    0.48
    损害
    0.47
     উভ
    0.45
     ধ্বংস
    0.44
     Bay
    0.43
     রোজ
    0.43
    AreEqual
    0.43
    šnje
    0.43
    城
    0.43
     मुर्
    0.42
    Activations Density 0.008%

    No Known Activations