© 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. 5002
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Sanskrit
    0.83
    槨
    0.77
    が表示
    0.76
     이는
    0.75
    FIFA
    0.74
     JUnit
    0.74
     SCSI
    0.73
     mivel
    0.73
     conformance
    0.72
     desta
    0.71
    POSITIVE LOGITS
    til
    0.89
    t
    0.87
    ut
    0.82
    iat
    0.82
    kirk
    0.78
    те
    0.77
    the
    0.74
    ở
    0.73
     оде
    0.72
     arme
    0.71
    Activations Density 0.335%

    No Known Activations