© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12142
    Prev
    Next
    INDEX
    Explanations

    past tense and comparison

    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_10/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
    ynchron
    -1.22
    мки
    -1.17
    礼物
    -1.09
    ='')
    -1.09
    铪
    -1.08
    目前
    -1.07
    Ту
    -1.05
    phalt
    -1.04
    おう
    -1.04
    ขอบคุณ
    -1.02
    POSITIVE LOGITS
     einfacher
    1.30
    urgence
    1.14
     gefü
    1.14
    :
    1.13
    ſon
    1.13
     '-';
    1.11
     '/';
    1.10
    ibrill
    1.10
     entonces
    1.09
    égal
    1.09
    Activations Density 0.040%

    No Known Activations