© 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. 99875
    Prev
    Next
    INDEX
    Explanations

    he was a

    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
    Been
    -1.02
    masing
    -1.01
    ebly
    -1.00
    ̴
    -0.99
    ̸
    -0.99
    אני
    -0.97
    orist
    -0.97
    代目
    -0.96
    eded
    -0.94
    Were
    -0.94
    POSITIVE LOGITS
     loved
    2.50
     was
    2.23
     will
    2.13
     always
    1.89
     leaves
    1.73
     could
    1.65
     also
    1.63
     had
    1.53
     never
    1.52
     love
    1.47
    Activations Density 0.004%

    No Known Activations