© 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
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9385
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     Undoubtedly
    0.79
    }}}^{
    0.79
     تمامی
    0.78
     Specifies
    0.77
    })}\
    0.76
    0.76
     تمام
    0.75
     Configurations
    0.74
    そのような
    0.74
    ﺩ
    0.74
    POSITIVE LOGITS
    airobi
    0.71
    nad
    0.70
    ня
    0.69
    now
    0.68
    ment
    0.68
    nz
    0.67
    nj
    0.65
    nr
    0.64
    पना
    0.64
    northern
    0.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.