© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 145077
    Prev
    Next
    INDEX
    Explanations

    starting before

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

    cave dwellings, cities, economics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    یہ
    0.51
    वन
    0.48
     эпи
    0.47
    वर्ल्ड
    0.47
     वर्ल्ड
    0.46
     प्लांट्स
    0.46
    देखो
    0.45
    汉
    0.44
    默默
    0.44
     верно
    0.44
    POSITIVE LOGITS
     atau
    0.46
     postoje
    0.45
     veya
    0.45
     PRET
    0.45
     dimost
    0.43
     construe
    0.43
     利
    0.42
    سبة
    0.42
     dismissal
    0.41
     dovoljno
    0.41
    Activations Density 0.001%

    No Known Activations