© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219516
    Prev
    Next
    INDEX
    Explanations

    adjective noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    risk, threat, not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     言
    0.49
    釗
    0.47
    ühren
    0.46
    ówno
    0.45
     காட்சிகள்
    0.45
     程序
    0.44
     函数
    0.44
    érance
    0.43
    woorden
    0.43
    넘
    0.43
    POSITIVE LOGITS
    ک
    0.48
     rises
    0.48
    اذ
    0.48
    pound
    0.47
    Bod
    0.47
     enamel
    0.47
     market
    0.46
     kaca
    0.46
     nara
    0.45
     at
    0.44
    Activations Density 0.002%

    No Known Activations