© 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. 2366
    Prev
    Next
    INDEX
    Explanations

    perception of seeing or hearing

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    a
    1.55
    '
    1.17
    e
    1.12
    s
    1.11
    iami
    1.08
    aal
    1.05
    iii
    1.03
    it
    1.02
    says
    1.02
     analyze
    1.00
    POSITIVE LOGITS
    дів
    0.99
     букме
    0.97
     والح
    0.90
    टर
    0.89
    ర్
    0.89
     دعا
    0.88
    讣
    0.88
    рби
    0.88
     ανθρώ
    0.87
     murmur
    0.87
    Activations Density 0.060%

    No Known Activations