© 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. 17802
    Prev
    Next
    INDEX
    Explanations

    GPT-2 and Llama 2 versions

    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
     is
    0.63
     of
    0.49
    0.48
    ن
    0.46
     C
    0.45
    endant
    0.43
     As
    0.42
    ه
    0.42
     as
    0.42
     De
    0.40
    POSITIVE LOGITS
    hur
    0.54
    ています
    0.54
    দের
    0.52
    ၊
    0.50
    ၾ
    0.50
    ᱒
    0.49
    력이
    0.48
    り
    0.48
    سة
    0.47
    ことが
    0.46
    Activations Density 0.030%

    No Known Activations