© 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. 210472
    Prev
    Next
    INDEX
    Explanations

    `numbers` `money` `interest`

    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
     Adapter
    0.44
     adapter
    0.42
     Ballroom
    0.39
     linearly
    0.39
    >{</
    0.38
     single
    0.37
     kontak
    0.37
     retry
    0.37
     production
    0.37
    ာ
    0.37
    POSITIVE LOGITS
    વો
    0.42
     מפ
    0.38
    אם
    0.37
    פות
    0.37
    ",'
    0.37
     폐
    0.37
    ridges
    0.36
    綜合
    0.36
    rista
    0.36
    jest
    0.36
    Activations Density 0.003%

    No Known Activations