© 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. 22-GEMMASCOPE-RES-131K
    7. 65507
    Prev
    Next
    INDEX
    Explanations

    "review" and "rating"

    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_22/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
     tartış
    -1.13
     beliebt
    -1.13
     μας
    -1.09
    aibo
    -1.02
     جدید
    -1.02
    地區
    -1.00
    ERe
    -0.96
     silahkan
    -0.96
    cedula
    -0.94
     discussão
    -0.94
    POSITIVE LOGITS
     rating
    1.30
     review
    1.27
     HAPPENED
    1.20
    More
    1.13
    review
    1.06
     фотография
    1.05
    tibles
    1.03
    SEP
    1.02
     reviews
    1.01
    igth
    1.01
    Activations Density 0.012%

    No Known Activations