© 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. 39749
    Prev
    Next
    INDEX
    Explanations

    relationship between

    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
    騭
    -2.66
    卝
    -2.58
    琹
    -2.55
    嵛
    -2.52
    ."
    -2.50
    旆
    -2.44
    ﮑ
    -2.38
    釙
    -2.36
    ᚻ
    -2.36
    ጄ
    -2.34
    POSITIVE LOGITS
    “
    3.36
    ’’
    2.59
     betont
    2.47
    但他
    2.41
     będą
    2.23
    ，，
    2.16
     ‘’
    2.14
    それにしても
    2.11
     solicita
    2.11
    但她
    2.08
    Activations Density 0.015%

    No Known Activations