© 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. 22-GEMMASCOPE-RES-131K
    7. 67491
    Prev
    Next
    INDEX
    Explanations

    in particular

    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
     both
    -1.16
     however
    -1.15
    から
    -1.13
    がありますが
    -1.10
    があるので
    -1.09
     både
    -1.07
    ทั้ง
    -1.06
    ですが
    -1.05
    に
    -1.04
    pendentif
    -1.02
    POSITIVE LOGITS
     that
    1.19
     importantly
    1.18
     longterm
    1.11
    なのだ
    1.10
     También
    1.08
    囿
    1.06
    iata
    1.05
    onesi
    1.05
    のですね
    1.03
    ㈱
    1.03
    Activations Density 0.050%

    No Known Activations