© 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-16K
    7. 10126
    Prev
    Next
    INDEX
    Explanations

    future wife / relations / distance

    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_16k_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
    Y
    0.89
    ی
    0.87
    Zone
    0.85
     conifers
    0.83
    Дан
    0.83
    I
    0.81
    કી
    0.81
    eur
    0.80
     watersheds
    0.78
    isci
    0.77
    POSITIVE LOGITS
     víctima
    0.99
    вых
    0.86
    be
    0.86
     traslad
    0.82
     DEVELOP
    0.81
     maravill
    0.81
     obligación
    0.81
    0.80
     enfoque
    0.80
     frecuencia
    0.80
    Activations Density 0.003%

    No Known Activations