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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84250
    Prev
    Next
    INDEX
    Explanations

    personal statements and opinions

    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_34/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
    Whilst
    -1.48
     whilst
    -1.44
    Fuck
    -1.36
    }:=\
    -1.33
    ModelAdmin
    -1.30
    🩹
    -1.30
     navire
    -1.30
    zló
    -1.30
    ):=
    -1.27
    formazione
    -1.25
    POSITIVE LOGITS
     [
    2.52
     really
    1.75
     pretty
    1.60
     basically
    1.52
     I
    1.47
     people
    1.45
     didn
    1.41
     wouldn
    1.35
     there
    1.34
     everybody
    1.33
    Activations Density 0.060%

    No Known Activations