© 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-262K
    7. 28181
    Prev
    Next
    INDEX
    Explanations

    describing systems and their components

    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_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
    𒁍
    0.51
    ଷ
    0.50
     ferrite
    0.50
    鰱
    0.48
    NEUTRON
    0.46
    ਿੰ
    0.45
    ಾರದ
    0.44
    DesIP
    0.44
     ladle
    0.44
    اران
    0.43
    POSITIVE LOGITS
     At
    0.52
    el
    0.49
     El
    0.47
     The
    0.47
     Every
    0.47
     All
    0.46
     in
    0.45
     '
    0.45
     For
    0.44
     My
    0.44
    Activations Density 0.000%

    No Known Activations