© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1903
    Prev
    Next
    INDEX
    Explanations

    scientific or industry terms

    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
     — 
    -0.94
    componentWill
    -0.93
    Exo
    -0.84
     ২০১
    -0.84
     this
    -0.82
     setengah
    -0.75
     ۲۰۱
    -0.74
     immediately
    -0.74
    calciatore
    -0.71
     Fuck
    -0.71
    POSITIVE LOGITS
    androidx
    0.98
     NFTs
    0.94
    })();
    0.87
     ۱۴۰۰
    0.87
    ;">
    0.87
     NFT
    0.86
     metaverse
    0.84
    atecas
    0.84
     loung
    0.84
     ২০
    0.84
    Activations Density 0.001%

    No Known Activations