© 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. 98220
    Prev
    Next
    INDEX
    Explanations

    keep an eye on

    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
     when
    -1.40
     since
    -1.26
    がある
    -1.23
    <bos>
    -1.21
    zegovina
    -1.19
    但是在
    -1.18
    时的
    -1.18
    所以在
    -1.16
    除此
    -1.09
    だからこそ
    -1.09
    POSITIVE LOGITS
    </i>
    1.23
    Keep
    1.20
    様に
    1.16
     abreast
    1.15
     gestorben
    1.13
     ciepła
    1.10
    ほうが
    1.09
    のですか
    1.08
     drewna
    1.07
     sierpnia
    1.05
    Activations Density 0.029%

    No Known Activations