© 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. 34-GEMMASCOPE-RES-131K
    7. 103381
    Prev
    Next
    INDEX
    Explanations

    Hill and its compounds

    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_34/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
     différence
    -0.82
    引用元
    -0.80
     réalisation
    -0.75
    キャベツ
    -0.75
    痛み
    -0.75
    ערך
    -0.73
    getF
    -0.73
     réussite
    -0.72
     Variants
    -0.71
    瞼
    -0.71
    POSITIVE LOGITS
    billy
    1.44
    top
    1.24
    side
    1.13
    ock
    1.08
    SIDE
    1.03
    ides
    1.00
    tops
    0.99
    yard
    0.99
    crest
    0.98
    yer
    0.93
    Activations Density 0.013%

    No Known Activations