© 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. 33776
    Prev
    Next
    INDEX
    Explanations

    first digit

    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
    >|</
    -0.87
     Depois
    -0.85
    AppComponent
    -0.85
     continue
    -0.85
    过后
    -0.84
    それも
    -0.83
    接著
    -0.83
    Next
    -0.83
    Затем
    -0.82
    Также
    -0.81
    POSITIVE LOGITS
     first
    1.43
     primeira
    1.23
     ersten
    1.20
    首先
    1.17
     primero
    1.16
     immediate
    1.16
     první
    1.10
     zuerst
    1.08
     primeiro
    1.03
    第一
    1.02
    Activations Density 0.007%

    No Known Activations