© 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. 20729
    Prev
    Next
    INDEX
    Explanations

    Palm and Windows mobile devices

    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
    Sliced
    0.39
     slicing
    0.38
    atitis
    0.37
    omatous
    0.37
     sliced
    0.37
     kaleidoscopic
    0.36
     চলচ্চিত্রের
    0.36
    𒆜
    0.36
    žu
    0.36
     mechanistic
    0.36
    POSITIVE LOGITS
     Pocket
    0.77
    Pocket
    0.74
     PDA
    0.71
     Palm
    0.71
     Mobile
    0.69
    Palm
    0.66
    Mobile
    0.66
     pocket
    0.63
    mobile
    0.63
    PDA
    0.61
    Activations Density 0.003%

    No Known Activations