© 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. 223305
    Prev
    Next
    INDEX
    Explanations

    html link tags

    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
     nj
    0.44
     III
    0.39
     chauff
    0.37
     fontFamily
    0.37
    um
    0.37
     W
    0.37
     propo
    0.35
     Fitzsimmons
    0.35
     NJ
    0.35
    openide
    0.35
    POSITIVE LOGITS
    썹
    0.40
    衅
    0.38
    속
    0.38
    iftung
    0.38
    碎片
    0.37
     سر
    0.37
     இரத்த
    0.37
     बनाए
    0.36
     تأثير
    0.36
    通常の
    0.36
    Activations Density 0.049%

    No Known Activations