© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108805
    Prev
    Next
    INDEX
    Explanations

    register, delegate, attach

    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
     conseguenze
    -0.72
     Coyle
    -0.71
     軍
    -0.67
     einz
    -0.67
     acids
    -0.67
    ترم
    -0.66
    ,-\
    -0.63
     samenwerking
    -0.63
     pensaba
    -0.63
    habitude
    -0.63
    POSITIVE LOGITS
    Attached
    6.09
     attached
    5.53
     Attached
    5.25
    attached
    4.75
     attach
    3.81
    attach
    3.56
     attaching
    3.36
     Attach
    3.28
     attaches
    3.23
     attachment
    3.19
    Activations Density 0.072%

    No Known Activations