© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 3382
    Prev
    Next
    INDEX
    Explanations

    thoughts of harm

    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_7_width_16k_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
    𝘳
    1.88
    developed
    1.86
     اقتصاد
    1.81
    ">%
    1.78
    det
    1.77
    ifika
    1.76
     جلو
    1.74
    𝘰
    1.74
    ্ভ
    1.73
    rass
    1.73
    POSITIVE LOGITS
    াযোগ
    2.48
    два
    2.34
    OscInitStruct
    2.23
     inFile
    2.22
    uições
    2.21
     instrucciones
    2.20
     Elytres
    2.19
     Intents
    2.16
     Crunchy
    2.14
     semelhantes
    2.14
    Activations Density 0.051%

    No Known Activations