© 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. 20586
    Prev
    Next
    INDEX
    Explanations

    web3, csv, base

    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
    Death
    0.49
    <0x80>
    0.48
    Fashion
    0.46
    Air
    0.42
    oscope
    0.42
    ท่า
    0.42
     дело
    0.41
    /
    0.40
    Meal
    0.40
    сное
    0.39
    POSITIVE LOGITS
     embraces
    0.50
     marched
    0.49
     accelerate
    0.48
     lahir
    0.48
     crecer
    0.48
     godina
    0.48
     Lernen
    0.47
     deterred
    0.47
     instigated
    0.47
     delivered
    0.47
    Activations Density 0.021%

    No Known Activations