© 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. 32435
    Prev
    Next
    INDEX
    Explanations

    contrary to popular belief

    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
    ’
    0.52
     incredibly
    0.48
     masterpieces
    0.46
    ércoles
    0.45
     unbelievably
    0.45
    devices
    0.43
    h
    0.43
     nye
    0.42
     insanely
    0.42
     dobbiamo
    0.42
    POSITIVE LOGITS
    洛
    0.43
    动物
    0.42
    สู
    0.41
     фаразлары
    0.40
     lago
    0.40
     getpath
    0.40
    欤
    0.40
    鍒
    0.39
    友
    0.39
    灵活
    0.38
    Activations Density 0.006%

    No Known Activations