© 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. 72103
    Prev
    Next
    INDEX
    Explanations

    describing a list

    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
    があります
    -1.48
     illustrate
    -1.39
     нашем
    -1.34
    ～。
    -1.34
     alludes
    -1.34
    我們的
    -1.33
     bolster
    -1.32
     بسیار
    -1.31
     ”
    -1.30
     некоторые
    -1.29
    POSITIVE LOGITS
    '
    1.77
     explicado
    1.47
     reservados
    1.44
    白衣
    1.42
    皷
    1.41
    ᓯ
    1.39
    嚳
    1.39
    comfor
    1.39
     selben
    1.38
     gesuchten
    1.38
    Activations Density 0.028%

    No Known Activations