© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5538
    Prev
    Next
    INDEX
    Explanations

    This neuron activates most strongly on relatively rare or information-rich tokens (i.e. low-frequency, unexpected words).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
     {}".
    0.65
    אס
    0.57
    ”.
    0.57
     {}",
    0.53
    \".
    0.53
    ”।
    0.53
    ”;
    0.52
    욘
    0.52
     herkese
    0.51
     सच्चाई
    0.50
    POSITIVE LOGITS
    ,)
    2.27
    ,),
    2.00
    ',)
    1.95
    ,))
    1.93
    ,]
    1.91
    ,}
    1.80
    ,=
    1.48
    },}
    1.41
    ,*
    1.31
    ,</
    1.31
    Activations Density 0.033%

    No Known Activations