© 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. 5854
    Prev
    Next
    INDEX
    Explanations

    drunk koalas or Lizardmen

    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
    وا
    0.52
     primeira
    0.52
     ដើម្បី
    0.48
    Ne
    0.48
     ഉ
    0.47
     poetic
    0.47
     positivas
    0.46
    노
    0.46
     commenced
    0.46
     Ne
    0.46
    POSITIVE LOGITS
    ˵
    0.44
    䣬
    0.43
    守
    0.43
     géographique
    0.40
    制作
    0.40
    作り
    0.40
    描写
    0.39
     направление
    0.39
    OpenCamera
    0.39
    ၜ
    0.39
    Activations Density 0.023%

    No Known Activations