© 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-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79876
    Prev
    Next
    INDEX
    Explanations

    Arab Spring Middle East North Africa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
     monastic
    0.34
    parity
    0.34
    parvec
    0.33
    ڼ
    0.33
    plates
    0.32
     militar
    0.32
     paranoia
    0.32
     fontes
    0.32
     المسي
    0.31
    Variance
    0.31
    POSITIVE LOGITS
     Tunisie
    0.40
     FRESH
    0.36
     Tunisia
    0.35
     EAST
    0.34
     Tunisian
    0.34
     Egypt
    0.34
     ಹ
    0.33
    واه
    0.33
     User
    0.33
     Moroccan
    0.33
    Activations Density 0.001%

    No Known Activations