© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7515
    Prev
    Next
    INDEX
    Explanations

    subjunctive verbs in multiple languages

    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_22_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
    ']);
    1.07
    によると
    0.98
    '],
    0.86
    是要
    0.85
    是不
    0.85
    だと
    0.84
    '];
    0.83
    "]);
    0.82
    ˈ
    0.80
    testng
    0.80
    POSITIVE LOGITS
     abbia
    2.34
     possa
    2.16
     tenha
    2.14
     seja
    2.12
     esteja
    2.04
     fasse
    2.04
     puisse
    2.03
     siano
    2.01
     aient
    1.97
     tenga
    1.94
    Activations Density 0.020%

    No Known Activations