© 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. 16-GEMMASCOPE-2-RES-262K
    7. 138138
    Prev
    Next
    INDEX
    Explanations

    km³/year, Plutonium-241, glacier, about

    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_16_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
    有很多
    0.47
    小便
    0.45
     almu
    0.45
    保温
    0.45
     جمع
    0.44
     որ
    0.44
     손
    0.43
    osim
    0.43
    alom
    0.43
     வெப்ப
    0.43
    POSITIVE LOGITS
    É
    0.54
    త్
    0.50
    #'
    0.49
    인
    0.48
    芮
    0.48
    È
    0.48
    あれば
    0.47
    КИ
    0.46
    ñas
    0.46
    Cher
    0.46
    Activations Density 0.000%

    No Known Activations