© 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. 77752
    Prev
    Next
    INDEX
    Explanations

    potential outcomes and consequences

    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
     अपनी
    -1.30
    футболка
    -1.11
    ėja
    -1.07
     simpel
    -1.05
     becomes
    -1.05
    becomes
    -1.04
    变得
    -1.02
     wordt
    -1.01
    oise
    -1.00
    嗌
    -1.00
    POSITIVE LOGITS
     result
    1.66
     resulted
    1.61
     mean
    1.57
     allow
    1.37
     help
    1.32
     lead
    1.29
     means
    1.27
     spowod
    1.23
     zufried
    1.18
     results
    1.17
    Activations Density 0.164%

    No Known Activations