© 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. 22-GEMMASCOPE-RES-131K
    7. 33099
    Prev
    Next
    INDEX
    Explanations

    would or should follow

    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_22/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
    hsl
    -0.96
    Magdalena
    -0.93
    attuale
    -0.91
     poderosos
    -0.90
     since
    -0.88
     fotografii
    -0.88
    Takk
    -0.87
    ய்ய
    -0.87
    appartamento
    -0.86
    telah
    -0.84
    POSITIVE LOGITS
     will
    1.61
     would
    1.44
     should
    1.41
     always
    1.17
     shouldn
    1.11
    would
    1.07
    应该是
    1.06
     never
    1.04
    should
    0.99
    那些
    0.92
    Activations Density 0.075%

    No Known Activations