© 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. 1108
    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
    c
    0.22
    os
    0.22
    an
    0.22
    ian
    0.22
    ri
    0.22
    lle
    0.21
    to
    0.21
    lin
    0.21
    P
    0.21
    ен
    0.20
    POSITIVE LOGITS
     murderous
    0.24
     nasz
    0.24
     caoutchouc
    0.23
     superfluous
    0.22
     cellophane
    0.22
     ominous
    0.22
     AcOH
    0.22
    ঘরের
    0.22
     Tregs
    0.21
     annihilated
    0.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.