© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 461
    Prev
    Next
    INDEX
    Explanations

    death, known, exasperated

    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_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
    }\
    0.28
    \
    0.28
    じ
    0.26
     ="
    0.26
    ♻
    0.26
     \
    0.25
     itself
    0.24
     に
    0.23
    ached
    0.23
     一
    0.23
    POSITIVE LOGITS
     insistence
    0.52
     penchant
    0.49
     contribution
    0.48
     flamboyant
    0.44
     presence
    0.44
     prodigious
    0.43
     enigmatic
    0.42
     tireless
    0.42
     antics
    0.41
    contribution
    0.41
    Activations Density 0.363%

    No Known Activations