© 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. 94402
    Prev
    Next
    INDEX
    Explanations

    served with

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

    describing states and consequences

    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
    过程
    0.49
     desarrollado
    0.47
    bezier
    0.46
    唐
    0.46
    三种
    0.45
    雀
    0.45
    мен
    0.45
    мом
    0.44
    关于
    0.43
    的过程中
    0.43
    POSITIVE LOGITS
    **.
    0.51
    uu
    0.50
    nnnn
    0.49
    เสียง
    0.49
     vocalist
    0.48
    uksi
    0.48
    lari
    0.47
     Vikipedi
    0.47
    nYou
    0.46
    eee
    0.46
    Activations Density 0.000%

    No Known Activations