© 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-262K
    7. 1635
    Prev
    Next
    INDEX
    Explanations

    capable without required

    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_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
    殘
    0.40
     കൂടി
    0.38
    關於
    0.38
     ۋە
    0.37
    文中
    0.37
     ศ
    0.36
     muestran
    0.36
    ش
    0.36
     narrative
    0.36
     montrent
    0.35
    POSITIVE LOGITS
    uleiro
    0.44
     uninterrupted
    0.44
    ोटोरोला
    0.43
     заниматься
    0.42
     shouldn
    0.42
     jeopard
    0.41
     Ори
    0.41
     nonstop
    0.41
     оптима
    0.40
    гови
    0.40
    Activations Density 0.004%

    No Known Activations