© 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. 16293
    Prev
    Next
    INDEX
    Explanations

    Z and converters

    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
    啵
    0.41
    StillWater
    0.38
    埛
    0.38
    Bb
    0.37
    郦
    0.37
    читься
    0.37
    െയ്
    0.37
    BrNO
    0.37
    ellite
    0.36
    Survived
    0.36
    POSITIVE LOGITS
     Z
    1.01
     z
    0.91
    Z
    0.75
     zn
    0.65
     Ζ
    0.64
     ZF
    0.64
     জেড
    0.63
     ZR
    0.62
     CZ
    0.61
     ZA
    0.61
    Activations Density 0.049%

    No Known Activations