© 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. 117191
    Prev
    Next
    INDEX
    Explanations

    following conditions

    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
     RIB
    -0.83
    wester
    -0.68
     executor
    -0.68
    YSTEM
    -0.67
    Hyper
    -0.67
    Spo
    -0.67
     QS
    -0.66
     בה
    -0.66
     reik
    -0.66
     IDS
    -0.66
    POSITIVE LOGITS
    bonds
    0.69
     remar
    0.67
    desde
    0.66
     üzerinden
    0.66
     experiences
    0.66
    bollah
    0.63
    围绕
    0.63
     Вален
    0.63
    gemeinschaft
    0.62
    irre
    0.61
    Activations Density 0.069%

    No Known Activations