© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116443
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
    lanan
    -1.33
     exé
    -1.30
     geniales
    -1.28
     уже
    -1.23
    voer
    -1.21
     diretor
    -1.20
    !=-
    -1.20
     lucr
    -1.20
     digne
    -1.17
     schrijven
    -1.16
    POSITIVE LOGITS
     also
    3.48
     then
    3.25
     later
    2.64
     was
    2.25
     continued
    2.20
     subsequently
    2.17
     is
    2.06
     currently
    1.91
     subsequent
    1.81
     therefore
    1.77
    Activations Density 0.133%

    No Known Activations