© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1719
    Prev
    Next
    INDEX
    Explanations

    aware, unsafeguarded, O, do, Mount, utterance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    吹き
    1.14
     ši
    1.06
     buk
    1.05
    branding
    1.04
    roboto
    1.00
    sentiment
    0.98
     stockfoto
    0.97
    𝚋
    0.97
    𝚙
    0.96
    isNull
    0.95
    POSITIVE LOGITS
     respectively
    1.13
     ಗೋ
    1.05
     arrived
    1.03
     departed
    1.01
    來的
    0.99
     invited
    0.94
    arono
    0.93
    ertung
    0.93
     confirmed
    0.92
     moderated
    0.92
    Activations Density 0.506%

    No Known Activations