© 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. 31-GEMMASCOPE-2-RES-16K
    7. 136
    Prev
    Next
    INDEX
    Explanations

    can be or may 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_31_width_16k_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
    '
    0.20
    ’
    0.19
    itation
    0.17
    ising
    0.16
    ation
    0.16
    mrow
    0.15
     explosives
    0.15
    .
    0.15
     isotherms
    0.15
    rows
    0.15
    POSITIVE LOGITS
     be
    0.26
     быть
    0.22
     būti
    0.22
     transcend
    0.19
     być
    0.18
     modernize
    0.18
     γίνει
    0.18
     conceivably
    0.18
     být
    0.18
     reunite
    0.18
    Activations Density 0.955%

    No Known Activations