© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 87532
    Prev
    Next
    INDEX
    Explanations

    expected value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nicht
    0.67
     Ah
    0.65
    ﻒ
    0.63
     Между
    0.63
     gebaut
    0.63
     говорит
    0.60
     Selv
    0.60
     métall
    0.59
     été
    0.59
     Schule
    0.59
    POSITIVE LOGITS
    נה
    0.66
    Expected
    0.57
     بیٹنگ
    0.55
    Nigeria
    0.54
    נדי
    0.53
    songwriter
    0.52
    ब
    0.50
    นัก
    0.50
     기대
    0.49
    PAssignment
    0.49
    Activations Density 0.013%

    No Known Activations