© 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. 98036
    Prev
    Next
    INDEX
    Explanations

    would be followed by verbs

    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
    ꙰
    -1.52
    踭
    -1.52
    刄
    -1.51
    荭
    -1.48
    薷
    -1.48
    翃
    -1.43
    Ꭾ
    -1.41
    ⃢
    -1.37
    aneity
    -1.36
    踽
    -1.36
    POSITIVE LOGITS
     be
    4.38
     have
    2.36
     not
    2.03
     also
    1.80
     likely
    1.70
     need
    1.53
     only
    1.49
     være
    1.49
     probably
    1.43
     être
    1.39
    Activations Density 0.044%

    No Known Activations