© 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. 213480
    Prev
    Next
    INDEX
    Explanations

    respecting, murdered, nuanced, sales

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

    young age and media details

    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
     computeEncoder
    0.49
     نتیجه
    0.45
     محک
    0.45
     idem
    0.44
     fullness
    0.44
    随意
    0.44
     andRow
    0.43
    妓
    0.43
    Antaeotricha
    0.43
    thoughtId
    0.43
    POSITIVE LOGITS
    𝗦
    0.51
    featuring
    0.49
     IMDb
    0.48
    ł
    0.46
    dod
    0.46
     Interact
    0.46
     featuring
    0.45
     Tijdens
    0.45
     אבל
    0.45
     ಹೆಚ್ಚು
    0.44
    Activations Density 0.001%

    No Known Activations