© 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. 110731
    Prev
    Next
    INDEX
    Explanations

    Japanese city names and characteristics

    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
    NaClO
    0.41
    ratulations
    0.40
     καρ
    0.40
    输
    0.39
     баскет
    0.39
    劉
    0.39
    hbs
    0.38
    镛
    0.38
    FileUpload
    0.37
    tbLabel
    0.37
    POSITIVE LOGITS
     wiped
    0.41
    सीना
    0.39
     erud
    0.39
     صفر
    0.39
     dampened
    0.39
     wiping
    0.38
    尻
    0.37
    剛
    0.37
    琲
    0.37
    ingin
    0.37
    Activations Density 0.000%

    No Known Activations