© 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. 81568
    Prev
    Next
    INDEX
    Explanations

    time stamps and durations

    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
     With
    -1.20
    It
    -1.10
    At
    -1.05
    With
    -1.03
     at
    -0.99
     mampu
    -0.92
     From
    -0.91
     Before
    -0.90
    状態
    -0.89
    企业
    -0.89
    POSITIVE LOGITS
    pm
    1.27
     rembour
    1.20
     دقیقه
    1.19
     goud
    1.09
     règne
    1.04
     aktiviteter
    1.03
     Duits
    1.03
     agir
    1.02
     récomp
    1.02
     patienter
    1.01
    Activations Density 0.019%

    No Known Activations