© 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. 40-GEMMASCOPE-2-RES-262K
    7. 0
    Prev
    Next
    INDEX
    Explanations

    This introduces a concept

    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
    ↵
    0.26
    <0x0D>
    0.21
    :
    0.21
     në
    0.20
                
    0.20
     bunları
    0.20
    ।
    0.20
    No
    0.20
    不错的
    0.19
     ابھی
    0.19
    POSITIVE LOGITS
     happens
    0.39
     makes
    0.38
     provides
    0.37
     ensures
    0.37
     gives
    0.37
     occurs
    0.36
     contrasts
    0.36
     resulted
    0.36
     creates
    0.35
     constitutes
    0.35
    Activations Density 0.108%

    No Known Activations