© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 58784
    Prev
    Next
    INDEX
    Explanations

    lake + place name

    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
     Barbarian
    -0.90
     Approaches
    -0.84
     procedimento
    -0.81
    ことです
    -0.79
     Yours
    -0.77
    DANGER
    -0.76
     Determined
    -0.76
    yours
    -0.75
     estoque
    -0.75
     calda
    -0.75
    POSITIVE LOGITS
    view
    1.16
    hore
    1.13
    front
    1.09
     shore
    1.05
    畔
    1.04
    View
    1.03
    hores
    1.03
    bed
    1.02
    head
    1.01
     Geneva
    1.01
    Activations Density 0.009%

    No Known Activations