© 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. 32707
    Prev
    Next
    INDEX
    Explanations

    dipole and quadrupole moments

    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
    matchCondition
    -0.82
    clientY
    -0.77
    bewerken
    -0.73
     dentelle
    -0.72
    UNC
    -0.71
     dinyatakan
    -0.71
     ditetapkan
    -0.69
     defend
    -0.68
    ின்
    -0.67
    providedIn
    -0.67
    POSITIVE LOGITS
     dipole
    2.75
     dip
    2.17
    Dip
    1.78
     Dip
    1.73
    dip
    1.64
     DIP
    1.63
     quadru
    1.56
    DIP
    1.53
     Di
    1.52
     dipped
    1.36
    Activations Density 0.045%

    No Known Activations