© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 42394
    Prev
    Next
    INDEX
    Explanations

    names of singers and artists

    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
    на
    1.09
    и
    1.09
    да
    1.06
    ASCII
    1.05
    ম্প
    1.05
    Lucy
    1.05
    ש
    1.04
    хо
    1.03
    NaClO
    1.03
    ד
    1.02
    POSITIVE LOGITS
     inaction
    0.96
     fates
    0.95
     encroachment
    0.93
     fate
    0.93
     olmayan
    0.92
     insinu
    0.91
     encroach
    0.91
    λευτα
    0.89
     metų
    0.87
    ają
    0.85
    Activations Density 0.003%

    No Known Activations