© 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. 31-GEMMASCOPE-2-RES-65K
    7. 27530
    Prev
    Next
    INDEX
    Explanations

    code documents start tag

    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_31_width_65k_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
    2
    0.53
    1
    0.52
    '
    0.52
    --
    0.44
     ascribed
    0.44
    ¹
    0.43
    _
    0.41
    the
    0.41
    OS
    0.40
     the
    0.40
    POSITIVE LOGITS
    btnLogout
    0.51
    btnAdd
    0.50
     এলইডি
    0.48
    োর্টের
    0.47
     Vestone
    0.47
     रिएक्टर
    0.47
     \%)$
    0.45
     EditorGUILayout
    0.45
     Oké
    0.45
     কণ্ঠে
    0.44
    Activations Density 0.001%

    No Known Activations