© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3054
    Prev
    Next
    INDEX
    Explanations

    conflict intensifies

    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
     WAS
    1.99
    was
    1.70
     SI
    1.62
    ва
    1.55
    t
    1.51
    Was
    1.50
     IS
    1.49
    linear
    1.47
    ް
    1.46
     neural
    1.44
    POSITIVE LOGITS
     którzy
    3.11
     ktorí
    2.94
     kteří
    2.75
     الذين
    2.65
    들에게
    2.62
     தங்கள்
    2.56
     كلهم
    2.48
     അവരുടെ
    2.40
     majú
    2.39
     ತಮ್ಮ
    2.39
    Activations Density 0.727%

    No Known Activations