© 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. 1004
    Prev
    Next
    INDEX
    Explanations

    making friends

    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
     produtos
    -0.84
     exitoso
    -0.79
     trinh
    -0.79
    msubsup
    -0.76
    MPL
    -0.76
    addington
    -0.76
    oluto
    -0.75
     surfaces
    -0.75
    visit
    -0.75
     patiently
    -0.74
    POSITIVE LOGITS
     making
    2.58
     make
    2.47
    Making
    2.33
     friendships
    2.22
     Making
    2.20
     made
    2.19
    making
    2.13
    make
    2.03
    交
    1.74
    Make
    1.73
    Activations Density 0.024%

    No Known Activations