© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31993
    Prev
    Next
    INDEX
    Explanations

    introducing or describing things

    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
     często
    -1.13
     nationalen
    -1.01
     wielu
    -0.89
     Often
    -0.88
     Dokumente
    -0.88
     internationalen
    -0.86
     you
    -0.85
     voeding
    -0.85
     miejscowości
    -0.85
     Essentially
    -0.85
    POSITIVE LOGITS
    ÜR
    1.16
     adalah
    1.13
     aima
    1.13
     kanton
    1.05
    pads
    1.03
    üste
    1.03
    hever
    1.02
     schal
    1.02
     queridos
    1.02
    yea
    1.01
    Activations Density 0.002%

    No Known Activations