© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1441
    Prev
    Next
    INDEX
    Explanations

    unethical practices and behavior

    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
    UW
    1.96
    I
    1.92
    {'
    1.90
    Emo
    1.86
    E
    1.82
    A
    1.79
    cross
    1.76
    C
    1.73
    Commander
    1.73
    AA
    1.71
    POSITIVE LOGITS
    ქმედ
    3.00
     coveredmethods
    2.76
     meadows
    2.71
    ेक्षित
    2.71
    ি
    2.69
    勰
    2.60
    徭
    2.55
    atsion
    2.55
    ی
    2.53
    ্থিত
    2.51
    Activations Density 0.001%

    No Known Activations