© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9315
    Prev
    Next
    INDEX
    Explanations

    destruction and damage

    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
     you
    -1.15
     murdering
    -1.14
     kidnapping
    -1.12
     murderers
    -1.10
     marshes
    -1.10
     Ivor
    -1.07
     murderer
    -1.06
     slaugh
    -1.06
     interacción
    -1.06
     meadows
    -1.05
    POSITIVE LOGITS
     damage
    1.27
     厨房
    1.19
    bindValue
    1.14
     several
    1.09
     ими
    1.09
     wykonane
    1.09
     damaged
    1.05
     Juifs
    1.03
     TÉCNICA
    1.03
    ：……
    1.01
    Activations Density 0.030%

    No Known Activations