© 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. 28383
    Prev
    Next
    INDEX
    Explanations

    attended dental school

    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
    〉
    0.42
    LFT
    0.42
    aranteed
    0.41
     Государ
    0.41
     gewesen
    0.40
     mulberry
    0.40
    <unused57>
    0.40
    컸
    0.40
    :"",
    0.40
     নির্দিষ্ট
    0.39
    POSITIVE LOGITS
     food
    0.46
     volcanic
    0.45
     hub
    0.44
     layers
    0.43
     nếu
    0.43
     vực
    0.42
    و
    0.42
     load
    0.42
     volcano
    0.41
     shop
    0.41
    Activations Density 0.021%

    No Known Activations