© 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. 210265
    Prev
    Next
    INDEX
    Explanations

    parent/partner

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

    states and transitions

    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
    сіб
    0.50
    μου
    0.50
     کننده
    0.49
     مختصر
    0.48
     देणे
    0.48
     لیگ
    0.47
    눗
    0.47
    𝗻
    0.47
    bedaan
    0.46
    اوار
    0.46
    POSITIVE LOGITS
     embeds
    0.58
     leads
    0.54
     d
    0.53
     adds
    0.52
     pathologists
    0.52
     anchors
    0.52
     induces
    0.50
     Adams
    0.49
     undermines
    0.49
     kills
    0.49
    Activations Density 0.000%

    No Known Activations