© 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. 507
    Prev
    Next
    INDEX
    Explanations

    ISBNs and UPCs

    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
     uyt
    -1.05
    かを
    -1.02
     geschenk
    -1.00
    ⟹
    -0.99
    >
    -0.99
    後的
    -0.96
    visions
    -0.93
    \,,
    -0.92
    んですか
    -0.92
     josé
    -0.92
    POSITIVE LOGITS
    9
    1.12
    2
    1.09
    ATIVO
    1.05
     れる
    1.04
    ISTAS
    1.04
    5
    1.02
    7
    1.01
     audiences
    1.00
    3
    0.98
     cómodo
    0.97
    Activations Density 0.002%

    No Known Activations