© 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. 34-GEMMASCOPE-RES-131K
    7. 55654
    Prev
    Next
    INDEX
    Explanations

    bombardment silenced the enemy

    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
    digd
    -1.03
    攔
    -0.96
     limpi
    -0.81
     поднима
    -0.81
     мебели
    -0.81
    することも
    -0.80
    uscht
    -0.80
    ἐ
    -0.80
     étan
    -0.79
    摒
    -0.79
    POSITIVE LOGITS
     destabili
    1.57
     forcing
    1.48
     demoral
    1.45
     disrupt
    1.23
    逼
    1.22
     forced
    1.18
     force
    1.18
    利用
    1.16
     выну
    1.16
     pressure
    1.15
    Activations Density 0.025%

    No Known Activations