© 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. 76454
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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
     también
    -1.34
     também
    -1.29
    <bos>
    -1.21
    лябин
    -1.16
    Также
    -1.13
     keluarga
    -1.12
    смарт
    -1.07
    Шу
    -1.03
    lblNewLabel
    -1.02
    也能
    -1.02
    POSITIVE LOGITS
     a
    1.55
     eigentlich
    1.09
     these
    1.07
    万一
    1.07
     one
    1.07
     vermutlich
    1.06
    ώ
    1.04
     those
    1.02
     something
    1.02
     really
    1.01
    Activations Density 0.005%

    No Known Activations