© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78592
    Prev
    Next
    INDEX
    Explanations

    introductory phrases starting with In

    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
    自然的
    -1.06
     sær
    -1.05
    倨
    -1.05
     fortsatt
    -1.05
    unches
    -1.02
     penutup
    -1.02
     senjata
    -1.01
     bendera
    -0.98
     revelado
    -0.98
    rupal
    -0.97
    POSITIVE LOGITS
     his
    1.66
     this
    1.26
     its
    1.21
     thus
    1.21
     discussing
    1.18
    踯
    1.08
     considering
    1.08
     spite
    1.05
     none
    1.05
     describing
    1.05
    Activations Density 0.063%

    No Known Activations