© 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. 86827
    Prev
    Next
    INDEX
    Explanations

    numbers of other things

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

    hundreds of participants and friendly stranger

    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
    協會
    0.50
     Association
    0.46
     association
    0.45
     revitalization
    0.44
     Assn
    0.42
     directional
    0.40
    Association
    0.40
     ج
    0.39
    အ
    0.38
    协会
    0.38
    POSITIVE LOGITS
    attered
    0.46
    config
    0.44
    rać
    0.44
    ቑ
    0.43
    યર
    0.43
     painkillers
    0.42
    kubernetes
    0.41
    ێک
    0.41
    ijnen
    0.41
    claves
    0.40
    Activations Density 0.001%

    No Known Activations