© 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. 120031
    Prev
    Next
    INDEX
    Explanations

    section headers or image captions

    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
    л
    0.55
    ل
    0.52
     φυ
    0.52
     ﺍﻟ
    0.50
    д
    0.50
     বিলম্ব
    0.49
    ers
    0.49
    я
    0.48
    f
    0.47
     estructura
    0.47
    POSITIVE LOGITS
     by
    0.57
    ř
    0.56
     lecturing
    0.55
     получи
    0.54
     lecturer
    0.54
     perpetuity
    0.53
     descending
    0.52
    ierten
    0.50
     hashing
    0.50
     вполне
    0.49
    Activations Density 0.008%

    No Known Activations