© 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. 63954
    Prev
    Next
    INDEX
    Explanations

    business listings

    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
    ällor
    -0.88
     informar
    -0.84
    一流
    -0.83
     Huk
    -0.83
    Here
    -0.82
    atemala
    -0.81
     setUsername
    -0.79
     Söhne
    -0.79
     superbly
    -0.77
     affiliated
    -0.76
    POSITIVE LOGITS
     realtor
    0.88
     valoraciones
    0.81
     oggi
    0.78
     tạp
    0.75
     Tach
    0.75
     Vrbo
    0.74
    bef
    0.73
    yta
    0.73
     verschied
    0.73
     Donation
    0.73
    Activations Density 0.005%

    No Known Activations