© 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. 80977
    Prev
    Next
    INDEX
    Explanations

    get something

    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
     during
    -1.12
     with
    -1.09
     after
    -1.01
     proč
    -0.97
     at
    -0.96
     throughout
    -0.94
     allowing
    -0.94
     when
    -0.93
     would
    -0.92
     through
    -0.92
    POSITIVE LOGITS
     started
    1.64
     your
    1.58
    started
    1.45
     Started
    1.41
    Started
    1.25
    STARTED
    1.25
     involved
    1.22
     rid
    1.19
     yourself
    1.09
     FREE
    1.09
    Activations Density 0.039%

    No Known Activations