© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16247
    Prev
    Next
    INDEX
    Explanations

    need or require

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dientes
    -1.05
    varnothing
    -1.03
     doporu
    -0.98
    KommentareTeilen
    -0.97
    Παραπομπές
    -0.94
    τής
    -0.94
     كورونا
    -0.93
    ñadir
    -0.92
    AddTagHelper
    -0.92
     suggested
    -0.92
    POSITIVE LOGITS
     for
    1.18
    用到
    1.08
     such
    0.95
     slike
    0.94
     periode
    0.93
     access
    0.92
     use
    0.88
     ability
    0.87
     fraiche
    0.86
     weten
    0.85
    Activations Density 0.133%

    No Known Activations