© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14451
    Prev
    Next
    INDEX
    Explanations

    ethical hacking, or bothering

    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_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
    opic
    1.25
    risi
    1.18
    łam
    1.18
    lar
    1.14
    nc
    1.14
    opi
    1.13
    proc
    1.11
    症
    1.11
    affe
    1.11
    op
    1.10
    POSITIVE LOGITS
     レザー
    1.72
     enthusiasm
    1.71
     야
    1.69
     防水
    1.67
     半袖
    1.66
     urged
    1.66
     steers
    1.66
     向
    1.65
     meaningful
    1.63
     지역
    1.63
    Activations Density 0.000%

    No Known Activations