© 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. 16940
    Prev
    Next
    INDEX
    Explanations

    according to different languages

    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
    émica
    0.40
     DBox
    0.40
     اچھا
    0.40
    вичай
    0.39
    zón
    0.38
    umination
    0.37
    飨
    0.37
     precipitate
    0.37
    更大
    0.37
    આત
    0.37
    POSITIVE LOGITS
     selon
    0.58
    string
    0.54
     según
    0.53
     according
    0.52
    '
    0.52
    according
    0.49
     który
    0.48
     Según
    0.48
     locali
    0.48
     Selon
    0.48
    Activations Density 0.004%

    No Known Activations