© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 97302
    Prev
    Next
    INDEX
    Explanations

    organized and safer

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

    lists and numbering

    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
    顶部
    0.49
    బు
    0.48
    面对
    0.47
    宝贝
    0.47
    少年
    0.46
    槿
    0.46
    宗
    0.45
    parentNode
    0.42
    म्स
    0.42
    ِب
    0.42
    POSITIVE LOGITS
     subst
    0.55
     apportionment
    0.54
     rites
    0.54
     tetanus
    0.54
     increases
    0.52
     anemia
    0.51
     typhoid
    0.50
     conund
    0.50
     transfusion
    0.50
     incarceration
    0.48
    Activations Density 0.000%

    No Known Activations