© 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. 34-GEMMASCOPE-RES-131K
    7. 58177
    Prev
    Next
    INDEX
    Explanations

    actions completed

    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
     Never
    -1.16
    never
    -1.16
     nooit
    -1.15
     being
    -1.14
     nunca
    -1.14
    previously
    -1.02
     pernah
    -1.02
     mindig
    -1.01
     vždy
    -1.00
     nigdy
    -0.99
    POSITIVE LOGITS
     finished
    1.70
     completed
    1.36
     reached
    1.32
     gone
    1.23
    finished
    1.21
     begun
    1.09
     fulfilled
    1.05
     progressed
    1.02
     arrived
    1.01
     disappeared
    1.01
    Activations Density 0.042%

    No Known Activations