© 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
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1118
    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
    いた
    0.85
     티
    0.71
     یخچال
    0.70
    اد
    0.69
    ся
    0.68
    ieft
    0.66
    दा
    0.64
    𒁺
    0.64
    ﺔ
    0.63
     Oats
    0.63
    POSITIVE LOGITS
    кси
    0.81
     äuß
    0.79
     conocidos
    0.76
    larıyla
    0.75
     deven
    0.75
     dissoci
    0.74
     einschließlich
    0.74
    (?:
    0.73
     höchste
    0.73
    um
    0.72
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.