© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2585
    Prev
    Next
    INDEX
    Explanations

    temporal conjunctions and pronouns

    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
     if
    -1.25
     and
    -1.17
     our
    -1.09
     like
    -1.05
     of
    -0.99
     unless
    -0.99
     dacă
    -0.97
     especially
    -0.97
    eaks
    -0.96
    asiest
    -0.96
    POSITIVE LOGITS
     when
    2.13
     after
    1.91
     после
    1.77
     לאחר
    1.77
     بعد
    1.67
     depois
    1.61
     عندما
    1.60
     когда
    1.59
     later
    1.53
     ketika
    1.52
    Activations Density 0.031%

    No Known Activations