© 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. 170066
    Prev
    Next
    INDEX
    Explanations

    swallowed whole

    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
    fehlung
    0.48
    的热
    0.47
    🩹
    0.47
    ഹ്
    0.46
     debug
    0.46
     بعد
    0.44
    짧
    0.43
    ifen
    0.42
    getImageFolder
    0.42
    isometric
    0.42
    POSITIVE LOGITS
    ।
    0.53
     Treats
    0.51
     Haci
    0.49
    s
    0.47
     Alder
    0.47
     Promises
    0.47
    ה
    0.46
     Catawiki
    0.45
     Snacks
    0.45
     affiliation
    0.44
    Activations Density 0.001%

    No Known Activations