© 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. 4042
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on descriptions of obstructed or disappointing room views.

    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_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
    Gene
    0.76
    FR
    0.73
    Day
    0.72
    CH
    0.70
    thanks
    0.70
    Via
    0.69
    GR
    0.69
    善
    0.69
    ABC
    0.68
    PI
    0.68
    POSITIVE LOGITS
     dilapidated
    1.34
     inappropriately
    1.27
     flimsy
    1.24
     appalling
    1.23
     substandard
    1.22
     blatantly
    1.22
     inappropriate
    1.21
     disrespectful
    1.21
     inaccurate
    1.20
     inadequ
    1.19
    Activations Density 0.127%

    No Known Activations