© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41329
    Prev
    Next
    INDEX
    Explanations

    Romance genre

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ج
    1.79
    ي
    1.54
    й
    1.51
    나
    1.50
    い
    1.48
    した
    1.44
    ed
    1.39
    да
    1.34
    ち
    1.32
    もっと
    1.30
    POSITIVE LOGITS
    ah
    1.52
     kanya
    1.52
    рана
    1.48
    ্ড
    1.45
    ાર્થ
    1.45
    юць
    1.43
    ificates
    1.40
     immunization
    1.40
    哋
    1.39
    ﻳ
    1.38
    Activations Density 0.007%

    No Known Activations