© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 103014
    Prev
    Next
    INDEX
    Explanations

    series, Allah, youtubers

    np_acts-logits-general · gemini-2.5-flash-lite

    society, suicide, damage, speech, world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ui
    0.55
    iter
    0.51
    ie
    0.47
    ER
    0.46
    ALLOW
    0.46
    ain
    0.45
    abu
    0.45
    ઉસ
    0.45
    allowed
    0.45
    ν
    0.44
    POSITIVE LOGITS
     ／
    0.47
     Гра
    0.47
     посред
    0.46
     Thunderbolt
    0.46
     referrerpolicy
    0.45
     लौटने
    0.44
    ９
    0.44
    اسو
    0.44
     gars
    0.43
    Boys
    0.43
    Activations Density 0.001%

    No Known Activations