© 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-65K
    7. 204
    Prev
    Next
    INDEX
    Explanations

    cannot and will not

    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_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
    u
    0.69
    ו
    0.66
    n
    0.55
    at
    0.52
    н
    0.52
    न
    0.52
    as
    0.47
    ’)
    0.47
    understand
    0.47
    o
    0.47
    POSITIVE LOGITS
     protože
    0.47
    ется
    0.46
    ító
    0.44
     rousing
    0.43
    娇
    0.43
    ค์
    0.42
    梠
    0.41
    ình
    0.41
     cheeks
    0.41
    ộn
    0.40
    Activations Density 0.173%

    No Known Activations