© 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. 191233
    Prev
    Next
    INDEX
    Explanations

    backing store

    np_acts-logits-general · gemini-2.5-flash-lite

    globally-inspired vegan comfort food

    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
    6
    0.56
    5
    0.55
    ್ರಿ
    0.48
    ↵
    0.48
    يب
    0.47
    9
    0.46
    7
    0.46
     attempts
    0.45
    0
    0.44
    4
    0.44
    POSITIVE LOGITS
    ableConcept
    0.54
     காட்சி
    0.52
    onavirus
    0.50
    Values
    0.49
     디
    0.48
     তৃত
    0.48
     कक्क
    0.47
     kehad
    0.47
     بہ
    0.46
     கிடை
    0.46
    Activations Density 0.002%

    No Known Activations