© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 232520
    Prev
    Next
    INDEX
    Explanations

    Do Not Call list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     weave
    0.49
     Той
    0.47
     borrow
    0.43
     thes
    0.43
     handleSubmit
    0.42
    なら
    0.40
     તેમણે
    0.40
    就
    0.40
    గానే
    0.39
    ة
    0.39
    POSITIVE LOGITS
     Appellate
    0.46
     ক্রমশ
    0.46
    geschwindigkeit
    0.46
    Deleted
    0.45
    Detach
    0.45
    textup
    0.44
     উৎক
    0.44
     বিস্ত
    0.44
     aktual
    0.43
    isierung
    0.43
    Activations Density 0.001%

    No Known Activations