© 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. 63179
    Prev
    Next
    INDEX
    Explanations

    questions asked

    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
    簒
    -0.81
     inquired
    -0.81
    tut
    -0.80
    查詢
    -0.80
    recen
    -0.79
    쏴
    -0.77
     enquired
    -0.71
    Hydra
    -0.71
    XS
    -0.70
    glBindTexture
    -0.70
    POSITIVE LOGITS
     posed
    3.17
     pose
    2.97
     зада
    2.73
     posing
    2.64
     ask
    2.63
     asking
    2.48
     poses
    2.42
    posed
    2.22
    Ask
    2.22
     Ask
    2.17
    Activations Density 0.068%

    No Known Activations