© 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. 957
    Prev
    Next
    INDEX
    Explanations

    disjoint sets, events, cycles

    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
    ization
    -3.13
    翃
    -3.05
    you
    -2.61
    薷
    -2.58
    毳
    -2.48
    dı
    -2.27
    ability
    -2.22
     medicines
    -2.19
    輅
    -2.17
    it
    -2.16
    POSITIVE LOGITS
    点的
    2.42
     espagnol
    2.34
     antworte
    2.22
    这让
    2.14
    𞤢
    2.13
    数値
    2.13
    除此
    2.08
    énégal
    2.05
     camas
    2.05
    并不
    2.05
    Activations Density 0.004%

    No Known Activations