© 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. 133866
    Prev
    Next
    INDEX
    Explanations

    sorting, gravity, size, sleep

    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
     þei
    0.40
     representatives
    0.40
     ideological
    0.39
     vâ
    0.39
    极
    0.39
     empowerment
    0.38
    у
    0.38
     practica
    0.38
     பயிற்
    0.38
    о
    0.37
    POSITIVE LOGITS
    currently
    0.43
    criptors
    0.42
     معاكم
    0.42
    find
    0.41
    assigned
    0.41
     използва
    0.40
     กว่า
    0.40
    fing
    0.39
     사용하는
    0.39
    ்களில்
    0.39
    Activations Density 0.002%

    No Known Activations