© 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. 108217
    Prev
    Next
    INDEX
    Explanations

    words ending in -ect, -act, -ract, -ict

    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
    いい
    -1.02
    tamanya
    -0.82
    ization
    -0.82
     aborto
    -0.80
    ható
    -0.77
    istic
    -0.76
    ists
    -0.75
    ropolitana
    -0.75
    holder
    -0.73
    ier
    -0.73
    POSITIVE LOGITS
    t
    1.23
    ors
    1.04
    lon
    0.90
    resses
    0.90
    rict
    0.88
    ress
    0.87
    lf
    0.87
    um
    0.85
    inite
    0.85
    strict
    0.82
    Activations Density 0.099%

    No Known Activations