© 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. 53159
    Prev
    Next
    INDEX
    Explanations

    localhost network addresses

    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
    ୱ
    0.43
     परेश
    0.42
    amiliar
    0.39
    umping
    0.39
     thửa
    0.39
    인을
    0.39
     Великобритании
    0.39
    igned
    0.39
    AccountId
    0.39
    ürdig
    0.38
    POSITIVE LOGITS
     Displacement
    0.47
     organize
    0.45
     displace
    0.44
     displacement
    0.43
     i
    0.41
     compose
    0.40
     vier
    0.39
     arb
    0.39
     plotting
    0.39
     saison
    0.39
    Activations Density 0.055%

    No Known Activations