© 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. 168032
    Prev
    Next
    INDEX
    Explanations

    logo design companies

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

    was first, attempted to, was influential

    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
    Not in Any Lists

    No Comments

    Negative Logits
     relic
    0.46
    ↵
    0.45
    ForKey
    0.45
     Vale
    0.45
     medit
    0.44
     Gov
    0.44
     Papa
    0.43
     Michele
    0.43
     printf
    0.42
     pí
    0.41
    POSITIVE LOGITS
    उद्योग
    0.54
    𝐦
    0.50
     ਅ
    0.47
     DENUMIRE
    0.47
    ål
    0.47
    ட்டாக
    0.47
    %","
    0.47
     TRANSPORTURI
    0.47
    ப்படுகின்றன
    0.46
    USR
    0.45
    Activations Density 0.001%

    No Known Activations